Papers with encoder
Learning to Order Graph Elements with Application to Multilingual Surface Realization (D19-63)
Copied to clipboard
| Challenge: | Recent advances in deep learning have shown promises in solving combinatorial optimization problems, such as sorting variable-sized sequences. |
| Approach: | They propose an encoder-decoder framework that learns the representation for each element and predicts the ordering of each local neighborhood of the graph in turn. |
| Outcome: | The proposed framework outperforms previous frameworks on multilingual surface realization tasks while outperforming those below by a large margin. |
Semantics-aware Attention Improves Neural Machine Translation (2022.starsem-1)
Copied to clipboard
| Challenge: | Existing attempts to integrate semantic structures into NMT Transformers have failed . |
| Approach: | They propose two parameter-free methods for injecting semantic information into Transformers, using a Scene-Aware Self-Attention (SASA) head and a Scenario-Award Cross-Action (SACrA) head. |
| Outcome: | The proposed methods improve on the vanilla Transformer and syntax-aware models for four language pairs and show an additional gain when using both semantic and syntactic structures in some language pairs. |
Cross-Lingual Transfer Learning for Speech Translation (2025.naacl-short)
Copied to clipboard
| Challenge: | Increasing interest in building multilingual foundation models for NLP and speech research has led to limited data collection for training ST systems. |
| Approach: | They propose to use Whisper to explore the behavior of multilingual speech foundation models with restricted data. |
| Outcome: | The proposed model can translate to Chinese with a single language, and it can perform transcriptions in other languages. |
Learning to Generate Question by Asking Question: A Primal-Dual Approach with Uncommon Word Generation (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing automatic question generation methods focus on encoding passage and answer to generate question. |
| Approach: | They propose an automatic question generation approach which integrates question generation with its dual problem, question answering, into a unified primal-dual framework. |
| Outcome: | The proposed approach outperforms existing methods on SQuAD and HotpotQA benchmarks. |
Transformer-based Model for Single Documents Neural Summarization (D19-56)
Copied to clipboard
| Challenge: | Existing approaches for document summarization use manual feature engineering, integer linear programming and data-driven approaches. |
| Approach: | They propose a framework that encodes the source text first with a transformer, then a sequence-to-sequence model. |
| Outcome: | The proposed framework improves performance on extractive and abstractive document summarization task using the CNN/DailyMail and Newsroom datasets. |
Probing Word Translations in the Transformer and Trading Decoder for Encoder Layers (2021.naacl-main)
Copied to clipboard
| Challenge: | Neural Machine Translation (NMT) has attracted wide attention in recent years. |
| Approach: | They propose a probing-based approach to measure word translation accuracy using transformer layers. |
| Outcome: | The proposed model outperforms previous probing-based translation models. |
Combining Subword Representations into Word-level Representations in the Transformer Architecture (2020.acl-srw)
Copied to clipboard
| Challenge: | Currently dominant approaches use word-level tokens, but this increases the length of the sequences and makes it difficult to profit from word-based information. |
| Approach: | They propose to combine subword-level representations into word-level ones in the first layers of the encoder, reducing the effective length of the sequences in the following layers. |
| Outcome: | The proposed model maintains translation quality with no extra word-level information . it is superior to the current dominant method for incorporating word- level source language information a priori . |
Multi-Prompting Decoder Helps Better Language Understanding (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to adapt Pre-trained Language Models to downstream tasks are limited by their inference APIs. |
| Approach: | They propose a multi-prompting decoding framework that query PLMs with multiple prompts . they propose to query Plms with optimal transport for hidden states and calibrated decoding for class scores . |
| Outcome: | The proposed framework achieves state-of-the-art results on multiple natural language understanding datasets under the few-shot setting. |
Towards Making the Most of Cross-Lingual Transfer for Zero-Shot Neural Machine Translation (2022.acl-long)
Copied to clipboard
| Challenge: | Existing unsupervised neural machine translation systems can degrade when labeled data is limited. |
| Approach: | They propose a multilingual pretraining and multilingual fine-tuning for facilitating cross-lingual transfer in zero-shot translation using a parallel dataset. |
| Outcome: | The proposed model outperforms state-of-the-art models on many-to-English translation by over 7.2 and 5.0 BLEU. |
SAMP: A Model Inference Toolkit of Post-Training Quantization for Text Processing via Self-Adaptive Mixed-Precision (2023.emnlp-industry)
Copied to clipboard
| Challenge: | Existing methods for quantization of models are too complicated and can cause performance damage. |
| Approach: | They propose a self-adaptive mixed-precision (SAMP) toolkit to automatically control quantization rate by a mixed-presence architecture to balance model accuracy and efficiency. |
| Outcome: | The proposed toolkit has a higher speedup than PyTorch and FasterTransformer while ensuring the required accuracy. |
Dictionary-based Debiasing of Pre-trained Word Embeddings (2021.eacl-main)
Copied to clipboard
| Challenge: | Existing methods for learning word embeddings using dictionaries do not require access to training resources or knowledge regarding the word embeds used. |
| Approach: | They propose a method for debiasing pre-trained word embeddings using dictionaries . they learn constraints that must be satisfied by unbiased word embeds from dictionary definitions . |
| Outcome: | The proposed method removes unfair biases encoded in pre-trained word embeddings while preserving useful semantics. |
A Partition Filter Network for Joint Entity and Relation Extraction (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to extract entity and relation feature are flawed because they do not consider the intimate connection between NER and RE. |
| Approach: | They propose a partition filter network to model two-way interaction between tasks . they leverage two gates: entity and relation gate, to segment neurons into two task partitions and one shared partition. |
| Outcome: | The proposed model performs significantly better than previous approaches on six public datasets. |
Unsupervised Pretraining for Neural Machine Translation Using Elastic Weight Consolidation (P19-2)
Copied to clipboard
| Challenge: | Neural machine translation (NMT) uses sequence to sequence architectures, but requires a huge amount of parallel data. |
| Approach: | They use Elastic Weight Consolidation to regularize weights of two language models . they then fine-tune the model on parallel data to avoid forgetting the original task . |
| Outcome: | The proposed method achieves BLEU scores similar to the previous work, but is slower and requires less training data. |
Hie-BART: Document Summarization with Hierarchical BART (2021.naacl-srw)
Copied to clipboard
| Challenge: | Existing document summarization models do not capture hierarchical structures of documents . proposed model incorporates multi-granularity self-attention (MG-SA) |
| Approach: | They propose a new abstractive document summarization model, hierarchical BART . the proposed model captures hierarchically structured sentences in the BART model . |
| Outcome: | The proposed model outperforms baseline models and improves performance on CNN/Daily Mail dataset. |
TencentPretrain: A Scalable and Flexible Toolkit for Pre-training Models of Different Modalities (2023.acl-demo)
Copied to clipboard
Zhe Zhao, Yudong Li, Cheng Hou, Jing Zhao, Rong Tian, Weijie Liu, Yiren Chen, Ningyuan Sun, Haoyan Liu, Weiquan Mao, Han Guo, Weigang Gou, Taiqiang Wu, Tao Zhu, Wenhang Shi, Chen Chen, Shan Huang, Sihong Chen, Liqun Liu, Feifei Li, Xiaoshuai Chen, Xingwu Sun, Zhanhui Kang, Xiaoyong Du, Linlin Shen, Kimmo Yan
| Challenge: | Several pre-training models of different modalities are showing a rising trend of homogeneity in their model structures. |
| Approach: | They propose a toolkit that supports pre-training models of different modalities. |
| Outcome: | The proposed toolkit can match the performance of the original implementations on text, vision, and audio benchmarks. |
From Partial to Strictly Incremental Constituent Parsing (2024.eacl-short)
Copied to clipboard
| Challenge: | Incremental NLP aims to learn and adapt partial representations as information unfolds, but studies on incremental approaches have focused on non-incremental approaches. |
| Approach: | They build incremental constituent parsers that adhere to a strong definition of incrementality across languages and compare them against non-incremental and partially incremental models. |
| Outcome: | The proposed models are compared against non-incremental and partially incremental models. |
Privacy-preserving Prosody Representation Learning (2026.acl-short)
Copied to clipboard
| Challenge: | Acoustic-prosodic cues are known to carry speaker information, exposing users to privacy breaches . a new self-supervised learning approach addresses privacy concerns . |
| Approach: | They propose a self-supervised approach to learning prosody representations that incorporates speaker disentanglement strategies. |
| Outcome: | The proposed model outperforms raw prosody and HuBERT-base baselines on three tasks . it achieves strong speaker disentanglement without adverse impact on prosody-related downstream tasks compared with baselines . |
Global Encoding for Abstractive Summarization (P18-2)
Copied to clipboard
| Challenge: | Existing models for abstractive summarization suffer from repetition and semantic irrelevance. |
| Approach: | They propose a global encoding framework which controls the information flow from the encoder to the decoder based on the global information of the source context. |
| Outcome: | The proposed model outperforms baseline models on the LCSTS and English Gigaword and can generate summary of higher quality and reduce repetition. |
Sentence-Incremental Neural Coreference Resolution (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing systems for identifying spans as mentions are based on mention-pair formulations, but they are not generalized beyond pronouns. |
| Approach: | They propose a sentence-incremental neural coreference resolution system which incrementally builds clusters after marking mention boundaries in a shift-reduce method. |
| Outcome: | The proposed system outperforms state-of-the-art methods on OntoNotes and CODI-CRAC 2021 datasets and is comparable to state- of-the art methods. |
Efficient Encoders for Streaming Sequence Tagging (2023.eacl-main)
Copied to clipboard
| Challenge: | Existing bidirectional encoders require a restart when a new token is received. |
| Approach: | They propose a Hybrid Encoder with Adaptive Restart that enables asynchronous encoding of a new token in an incremental streaming input. |
| Outcome: | The proposed encoder offers FLOP savings in streaming settings up to 71.1% and outperforms bidirectional encoders for streaming predictions by up to +0% streaming exact match. |
On the Locality of Attention in Direct Speech Translation (2022.acl-srw)
Copied to clipboard
| Challenge: | Recent advances in NLP have created problems with the complexity of the self-attention layer. |
| Approach: | They propose to substitute standard self-attention with a local efficient one to avoid the computation of attention weights. |
| Outcome: | The proposed model matches the baseline performance and improves efficiency by skipping the computation of weights that standard attention discards. |
Neural Topic Modeling with Bidirectional Adversarial Training (2020.acl-main)
Copied to clipboard
| Challenge: | Recent studies have shown that neural topic models for automatic topic extraction avoid complicated mathematical derivations for model inference. |
| Approach: | They propose a bidirectional adversarial topic model which uses a generator and an encoder to infer topic distribution. |
| Outcome: | The proposed model outperforms baselines and competitive models in three benchmark corpora. |
Unifying Parsing and Tree-Structured Models for Generating Sentence Semantic Representations (2022.naacl-srw)
Copied to clipboard
| Challenge: | Existing tree-based models require handannotated data to be trained. |
| Approach: | They propose a tree-based model that learns its composition function together with its structure. |
| Outcome: | The proposed model outperforms existing models on downstream tasks and is competitive with Bert base model. |
Self-Supervised Multimodal Opinion Summarization (2021.acl-long)
Copied to clipboard
| Challenge: | Existing methods for opinion summarization use text data, but non-text data are less abundant. |
| Approach: | They propose a self-supervised opinion summarization framework that uses non-text data to generate a summary from multiple reviews. |
| Outcome: | The proposed framework is superior to existing methods on Yelp and Amazon datasets. |
Neural Machine Translation with Synchronous Latent Phrase Structure (2021.acl-srw)
Copied to clipboard
| Challenge: | grammatical information annotation requires high human resources and is not trivial due to language mismatches and out-of-vocabulary problem. |
| Approach: | They propose to incorporate grammatical information without supervising annotation by induced latent phrase structure and synchronized phrase structures in encoder and decoder to enhance explainability. |
| Outcome: | The proposed method produces better performance and explainability in translation and alignment tasks without extra resources. |
RetroMAE: Pre-Training Retrieval-oriented Language Models Via Masked Auto-Encoder (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for dense retrieval are not effective, but there are still challenges. |
| Approach: | They propose a retrieval oriented pre-training paradigm based on Masked Auto-Encoder (MAE) where the sentence embedding is generated from the encoder’s masked input and the original sentence is recovered based upon the sentence embedded and decoded input via mangled language modeling. |
| Outcome: | The proposed model significantly improves the SOTA performance on a wide range of NLP benchmarks, like BEIR and MS MARCO. |
Jointly Masked Sequence-to-Sequence Model for Non-Autoregressive Neural Machine Translation (2020.acl-main)
Copied to clipboard
| Challenge: | masked language models have been used for natural language processing tasks but few studies have adopted it in the sequence-to-sequence models. |
| Approach: | They propose to combine encoder and decoder to train a masked sequence-to-sequence model . they propose to train the encoder more rigorously by masking the encoded input . |
| Outcome: | The proposed model achieves 27.69/32.24 BLEU scores on English-German/German-English tasks with 5+ times speed up compared with an autoregressive model. |
AMBERT: A Pre-trained Language Model with Multi-Grained Tokenization (2021.findings-acl)
Copied to clipboard
| Challenge: | Pre-trained language models such as BERT have shown great power in natural language understanding . fine-grained tokenizations have advantages and disadvantages for learning of pre-tried models . |
| Approach: | They propose a pretrained language model based on both fine-grained and coarse-grain tokenizations . they propose to use both tokenization techniques to learn pre-trained models . |
| Outcome: | The proposed model outperforms BERT on benchmark datasets for Chinese and English . it can perform better with the same computational cost as BERT, the authors show . |
Weakly-supervised Deep Cognate Detection Framework for Low-Resourced Languages Using Morphological Knowledge of Closely-Related Languages (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing approaches to cognate detection focus on orthographic, phonetic or contextual models, which under-perform for most under-resourced languages. |
| Approach: | They propose a language-agnostic weakly-supervised deep cognate detection framework for under-resourced languages using morphological knowledge from closely related languages. |
| Outcome: | The proposed framework outperforms state-of-the-art methods on cognate detection datasets across languages and can be extended to a wide range of languages from any language family. |
What Works and Doesn’t Work, A Deep Decoder for Neural Machine Translation (2022.findings-acl)
Copied to clipboard
| Challenge: | Deep learning has demonstrated performance advantages in a wide range of natural language processing tasks. |
| Approach: | They propose to deepen the decoder layer in a Transformer model to reduce the difficulty of deep learning. |
| Outcome: | The proposed method can deepen the model on both the encoder and decoder at the same time, resulting in a deeper model and improved performance. |
Contextual Parameter Generation for Universal Neural Machine Translation (D18-1)
Copied to clipboard
| Challenge: | Existing approaches to multilingual neural machine translation lack language-specific parameterization. |
| Approach: | They propose a modification to existing neural machine translation models that allows for language specific parameterization and domain adaptation. |
| Outcome: | The proposed model surpasses state-of-the-art for both the IWSLT-15 and IWSTL-17 datasets and can perform zero-shot translation. |
Predicting and Using Target Length in Neural Machine Translation (2020.aacl-main)
Copied to clipboard
| Challenge: | Current NMT systems do not model the length of the output explicitly . length normalization is a common technique used in the beam search of NMT to enable a fair comparison of partial hypotheses with different lengths. |
| Approach: | They propose to use length prediction as an auxiliary task to obtain length information from the encoder. |
| Outcome: | The proposed sub-network improves over the baseline system and the predicted length can be used as an alternative to length normalization during decoding. |
Is Encoder-Decoder Redundant for Neural Machine Translation? (2022.aacl-main)
Copied to clipboard
| Challenge: | Encoder-decoder architecture is widely adopted for sequence-to-sequence modeling tasks. |
| Approach: | They propose to combine bilingual and multilingual translations to train a language model to do translation. |
| Outcome: | The proposed approach performs on par with the baseline encoder-decoder Transformer . the proposed approach is compared with the translation model in the target language . |
Abstractive Document Summarization with Summary-length Prediction (2023.findings-eacl)
Copied to clipboard
| Challenge: | Existing abstractive summarization models do not consider summarizing-specific information such as the target summary length. |
| Approach: | They propose a method for enabling a model to understand summarization-specific information by predicting the summary length in the encoder and generating a summary of the predicted length in fine-tuning. |
| Outcome: | The proposed method improves ROUGE scores on the WikiHow, NYT, and CNN/DM datasets. |
Event-Centric Query Expansion in Web Search (2023.acl-industry)
Copied to clipboard
| Challenge: | Existing studies rely on long-term search log mining to improve search experience . EQE system is a novel event retrieval framework that can select the best expansion from a significant amount of potential events quickly and accurately. |
| Approach: | They propose a QE system that uses a four-stage event retrieval framework . they collect news headlines and then refine a dual-tower semantic model to serve as an encoder . |
| Outcome: | The proposed system can select the best expansion from a significant amount of potential events quickly and accurately. |
Multilingual Denoising Pre-training for Neural Machine Translation (2020.tacl-1)
Copied to clipboard
Yinhan Liu, Jiatao Gu, Naman Goyal, Xian Li, Sergey Edunov, Marjan Ghazvininejad, Mike Lewis, Luke Zettlemoyer
| Challenge: | Existing approaches to pre-train models focus on only English corpora, but this is not common in machine translation. |
| Approach: | They propose a sequence-to-sequence denoising auto-encoder pre-trained on monolingual corpora . they show that it produces significant performance gains across MT tasks . |
| Outcome: | The proposed model can achieve significant performance gains across a wide variety of MT tasks. |
CGF: Constrained Generation Framework for Query Rewriting in Conversational AI (2022.emnlp-industry)
Copied to clipboard
Jie Hao, Yang Liu, Xing Fan, Saurabh Gupta, Saleh Soltan, Rakesh Chada, Pradeep Natarajan, Chenlei Guo, Gokhan Tur
| Challenge: | Large-scale conversational AI agents such as Alexa, Siri and Google Assistant help millions of users to perform a lot of tasks. |
| Approach: | They propose a Constrained Generation Framework for query rewriting at global and personalized levels. |
| Outcome: | The proposed framework significantly boosts the query rewriting performance. |
Math Word Problem Solving by Generating Linguistic Variants of Problem Statements (2023.acl-srw)
Copied to clipboard
Syed Rifat Raiyan, Md Nafis Faiyaz, Shah Md. Jawad Kabir, Mohsinul Kabir, Hasan Mahmud, Md Kamrul Hasan
| Challenge: | Existing models for solving Math Word Problems depend on shallow heuristics and spurious correlations to derive the solution expressions. |
| Approach: | They propose a framework for MWP solvers based on generation of linguistic variants of problem text. |
| Outcome: | The proposed framework improves the mathematical reasoning and robustness of the proposed model. |
Transform Retrieval for Textual Entailment in RAG (2025.naacl-short)
Copied to clipboard
| Challenge: | Existing retrieval methods prioritize relevance without ensuring the retrieved documents semantically support answering the queries. |
| Approach: | They propose a novel approach to improve Textual Entailment Retrieval within the framework of Retri-Augmented Generation (RAG) they transform query embeddings to better align with semantic entailment without re-encoding the document corpus. |
| Outcome: | The proposed approach consistently approaches the skyline across multiple datasets, demonstrating its strength in many-to-many retrieval scenarios. |
Fusing Recency into Neural Machine Translation with an Inter-Sentence Gate Model (C18-1)
Copied to clipboard
| Challenge: | Neural machine translation systems translate one sentence at a time, ignoring inter-sentence information. |
| Approach: | They propose an inter-sentence gate model that uses the same encoder to encode two adjacent sentences . it captures the connection between sentences and fuses recency from neighboring sentences a model proposes . |
| Outcome: | The proposed model improves on NIST Chinese-English translation tasks . it captures the connection between sentences and fuses recency from neighboring sentences . |
Improving Neural Machine Translation by Incorporating Hierarchical Subword Features (C18-1)
Copied to clipboard
| Challenge: | Using subwords, we find that the appropriate subword units for the three layers differ depending on the model . incorporating hierarchical subword features improves BLEU scores on the IWSLT evaluation datasets. |
| Approach: | They propose a method that expresses a word by combining "subwords" they propose to incorporate hierarchical subword features into a single embedding layer . |
| Outcome: | The proposed method improves BLEU scores on the IWSLT evaluation datasets. |
Re-appraising the Schema Linking for Text-to-SQL (2023.findings-acl)
Copied to clipboard
| Challenge: | Recent work has shown that schema linking reduces robustness of text-to-SQL models . EMSL is used to correlate natural language queries with the given database schema . |
| Approach: | They propose a grammar linking module to help model align grammar references with SQL keywords. |
| Outcome: | The proposed language model improves performance without using EMSL, the authors show . their language model is more robust, and the proposed grammar linking improves interoperability . |
E2E Spoken Entity Extraction for Virtual Agents (2023.emnlp-industry)
Copied to clipboard
| Challenge: | Extensive research has been done to recognize entities in spoken input. |
| Approach: | They propose to fine-tune pre-trained speech encoders to extract spoken entities directly from speech without the need for text transcription. |
| Outcome: | The proposed approach outperforms the 2-step approach for extracting spoken entities from human-computer conversations. |
Training Adaptive Computation for Open-Domain Question Answering with Computational Constraints (2021.acl-short)
Copied to clipboard
| Challenge: | Adaptive Computation (AC) has been shown to be effective in improving the efficiency of Open-Domain Question Answering systems. |
| Approach: | They propose an AC method that can be applied to an existing ODQA model and can be trained efficiently on a single GPU. |
| Outcome: | The proposed method improves upon a state-of-the-art model on two datasets and is more accurate than previous AC methods due to the stronger base ODQA model. |
AdvPicker: Effectively Leveraging Unlabeled Data via Adversarial Discriminator for Cross-Lingual NER (2021.acl-long)
Copied to clipboard
| Challenge: | Named entity recognition models rely on expensive labeled data for training, which is not always available across languages. |
| Approach: | They propose an adversarial approach where an encoder learns entity domain knowledge from labeled source-language data and better shared features are captured via adversarially trained discriminators. |
| Outcome: | The proposed approach outperforms existing state-of-the-art methods on standard benchmark datasets and outperformed existing methods on the target language. |
Attention Fusion: a light yet efficient late fusion mechanism for task adaptation in NLU (2022.findings-naacl)
Copied to clipboard
| Challenge: | a recent study has shown that fine-tuning pre-trained models is parameter-inefficient and expensive. |
| Approach: | They propose a task-attuned token module which integrates pre-trained network representations into a pre-trainer. |
| Outcome: | The proposed model trains only 0.0009% of the parameters and is efficient during computation and scalable during deployment. |
iBERT: Interpretable Embeddings via Sense Decomposition (2026.eacl-long)
Copied to clipboard
| Challenge: | iBERT is an encoder that produces inherently interpretable and controllable embeddings without compromising performance. |
| Approach: | They propose an encoder that produces interpretable embeddings that modularize and expose discriminative cues present in language. |
| Outcome: | The proposed model outperforms baselines on style-focused tasks while maintaining competitive performance on authorship verification. |
Analysis and Prediction of NLP Models via Task Embeddings (2022.lrec-1)
Copied to clipboard
| Challenge: | Pretrained transformer-based encoders can be used to acquire rich text representations but need additional task supervision to be useful for downstream tasks. |
| Approach: | They propose a transformer to each MetaEval task and a neural network with a weighted encoder to perform the embeddings. |
| Outcome: | The proposed model outperforms baselines on GLUE tasks and can be used as a benchmark for future transfer learning research. |
LEANCODE: Understanding Models Better for Code Simplification of Pre-trained Large Language Models (2025.acl-long)
Copied to clipboard
| Challenge: | Large Language Models often require significant computational resources, often constraining input word or code token lengths. |
| Approach: | They propose to use the encoder-decoder attention scores to represent the importance of a code token across multiple contexts to reduce training and prediction time. |
| Outcome: | The proposed approach outperforms the SOTAs DietCode and SlimCode in code search and summarization tasks. |
EAVE: Efficient Product Attribute Value Extraction via Lightweight Sparse-layer Interaction (2024.findings-emnlp)
Copied to clipboard
Li Yang, Qifan Wang, Jianfeng Chi, Jiahao Liu, Jingang Wang, Fuli Feng, Zenglin Xu, Yi Fang, Lifu Huang, Dongfang Liu
| Challenge: | Existing methods to extract product attribute value require multiple extractions to obtain all corresponding values. |
| Approach: | They propose an Efficient product Attribute Value Extraction approach using lightweight sparse-layer interaction. |
| Outcome: | The proposed method achieves significant efficiency gains with neutral or marginal loss in performance when the context is long and number of attributes is large. |
On the Evaluation of Semantic Phenomena in Neural Machine Translation Using Natural Language Inference (N18-2)
Copied to clipboard
| Challenge: | Existing methods to investigate whether sentence representations from NMT systems capture distinct semantic phenomena are limited. |
| Approach: | They propose a process to investigate the extent to which sentence representations arising from neural machine translation systems encode distinct semantic phenomena. |
| Outcome: | The proposed model is suited to supporting inferences at the syntax-semantics interface, compared to anaphora resolution requiring world knowledge. |
Generative Multi-hop Retrieval (2022.emnlp-main)
Copied to clipboard
| Challenge: | A bi-encoder approach to text retrieval has limitations in multi-hop settings; the reformulated query gets longer as the number of hops increases, which further tightens the embedding bottleneck of the query vector. |
| Approach: | They propose an encoder-decoder model that performs multi-hop retrieval by simply generating the entire text sequences of the retrieval targets. |
| Outcome: | The proposed model achieves comparable or higher performance than bi-encoder models in five datasets while demonstrating superior GPU memory and storage footprint. |
Code Summarization with Structure-induced Transformer (2021.findings-acl)
Copied to clipboard
| Challenge: | Code summarization (CS) is a promising area in recent language understanding . previous work using structurebased traversal or non-sequential models to learn structural program semantics has shown no performance gain . |
| Approach: | They propose to use a structure-based traversal model to learn structural program semantics to generate human language automatically for programming language in the format of source code. |
| Outcome: | Experiments show that the proposed method achieves state-of-the-art on benchmarks. |
Aspect and Sentiment Aware Abstractive Review Summarization (C18-1)
Copied to clipboard
| Challenge: | Abstractive summarization is a task that generates short and concise summaries of user generated reviews. |
| Approach: | They propose an interactive attention mechanism to learn the representations of context and aspect words within reviews, acted as an encoder. |
| Outcome: | The proposed model achieves impressive results compared to other strong competitors on a real-life dataset. |
Cross-Lingual Representation Alignment Through Contrastive Image-Caption Tuning (2025.acl-short)
Copied to clipboard
| Challenge: | Multilingual alignment of sentence representations has mostly required bitexts to bridge the gap between languages. |
| Approach: | They propose to use image captions to implicitly align text representations between languages to make them usable for cross-lingual Natural Language Understanding (NLU) and bitext retrieval. |
| Outcome: | The proposed approach is usable for cross-lingual Natural Language Understanding (NLU) and bitext retrieval. |
End-to-End Beam Retrieval for Multi-Hop Question Answering (2024.naacl-long)
Copied to clipboard
| Challenge: | Existing beam retrieval frameworks for multi-hop question answering were customized for two-hop questions and were poorly supervised. |
| Approach: | They propose an end-to-end beam retrieval framework for multi-hop question answering . they combine an encoder and two classification heads to optimize the retrieval process . |
| Outcome: | The proposed framework improves on MuSiQue-Ans and surpasses all previous retrievers on HotpotQA and achieves 99.9% precision on 2WikiMultiHopQA. |
Precise Zero-Shot Dense Retrieval without Relevance Labels (2023.acl-long)
Copied to clipboard
| Challenge: | Existing dense retrieval systems that use semantic embedding similarities can be effective across tasks and languages. |
| Approach: | They propose to pivot through Hypothetical Document Embeddings (HyDE) given a query, HyDE first zero-shot prompts an instruction-following language model to generate a hypothetical document. |
| Outcome: | The proposed method significantly outperforms the state-of-the-art unsupervised dense retriever Contriever and shows strong performance comparable to fine-tuned retrievers across tasks and languages. |
Understanding Politics via Contextualized Discourse Processing (2021.emnlp-main)
Copied to clipboard
| Challenge: | Recent advances in pretrained language models do not capture nuanced biases in political discourse . a new approach to represent political content is to use contextualized embeddings to create effective representations . |
| Approach: | They propose a model that captures and leverages political content to generate more effective representations . they use tweets, press releases, issues, news articles and participating entities to generate composed representations. |
| Outcome: | The proposed model generates representations for political entities over multiple issues or events . qualitative and quantitative analysis shows that the model is meaningful and effective . |
Learning to Abstract with Nonparametric Variational Information Bottleneck (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Learning textual embeddings is costly as they are tokenization specific and require different models to be trained for each level of abstraction. |
| Approach: | They propose a character-level representation model which learns different levels of abstraction in different layers of the same model. |
| Outcome: | The proposed model is more robust to adversarial perturbations and can learn to compress representations to different levels of abstraction. |
Combining Character and Word Information in Neural Machine Translation Using a Multi-Level Attention (N18-1)
Copied to clipboard
| Challenge: | Neural machine translation models learn to map from source language sentences to target language sentences via continuous-space intermediate representations. |
| Approach: | They propose an encoder with character attention which augments the (sub)word-level representation with character-level information and a decoder with multiple attentions that enable the representations from different levels of granularity to control the translation cooperatively. |
| Outcome: | The proposed model outperforms the standard word-based model, subword-based models, and strong character-based ones on translation tasks. |
Dense Information Flow for Neural Machine Translation (N18-1)
Copied to clipboard
| Challenge: | Recent advances in deep neural networks have improved learning performance for NMT . Residual connections allow features from previous layers to be accumulated to the next layer easily. |
| Approach: | They propose a densely connected NMT architecture that can train more efficiently for NMT. |
| Outcome: | The proposed architecture improves learning performance and attention quality on multiple datasets. |
Addressing Semantic Drift in Generative Question Answering with Auxiliary Extraction (2021.acl-short)
Copied to clipboard
| Challenge: | Recent work focuses on question answering based on machine reading comprehension . current approaches treat QA as extracting a consecutive piece of text to a given question. |
| Approach: | They propose a generative QA model that incorporates an extractive mechanism into a model. |
| Outcome: | The proposed model improves quality and semantic accuracy over baseline models. |
Handling Homographs in Neural Machine Translation (N18-1)
Copied to clipboard
| Challenge: | Existing methods for MT have problems with translating homographs, as it is difficult to select the correct translation based on the context. |
| Approach: | They propose to model the context of the input word with context-aware word embeddings that help to differentiate the word sense before feeding it into the encoder. |
| Outcome: | The proposed models improve translation accuracy and BLEU score on three language pairs. |
PortOldBERT: Portuguese Historical Language Models (2026.eacl-long)
Copied to clipboard
| Challenge: | Historical language models are important for many tasks, but have limited application in historical Portuguese. |
| Approach: | They propose a Portuguese encoder language model that integrates historical linguistic contexts while retaining the ability to process contemporary text. |
| Outcome: | The proposed model outperforms Albertina on multiple tasks and for different historical periods. |
Hyperdecoders: Instance-specific decoders for multi-task NLP (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Recent work in NLP has examined the performance of large pretrained transformer-based models in multi-task settings, where a single model is evaluated on multiple tasks simultaneously. |
| Approach: | They propose a method for multi-tasking using a hypernetwork conditioned on the output of an encoder to generate a unique decoder adaptation for every input instance. |
| Outcome: | The proposed method outperforms previous methods for efficient multi-task fine-tuning and maps from encoder representations to output labels. |
Incorporating Graph Information in Transformer-based AMR Parsing (2023.findings-acl)
Copied to clipboard
| Challenge: | Abstract Meaning Representation (AMR) is a semantic graph abstraction for text representations. |
| Approach: | They propose a model and method that incorporates graph information into the learned representations of AMR by word-to-node alignment. |
| Outcome: | The proposed model improves AMR parsing performance by embedding graph information into the encoder at training time. |
Improving Zero-Shot Cross-Lingual Transfer Learning via Robust Training (2021.emnlp-main)
Copied to clipboard
| Challenge: | Pre-trained multilingual language encoders do not precisely align words and phrases across languages. |
| Approach: | They propose a learning strategy for training robust models by drawing connections between adversarial examples and failure cases of zero-shot cross-lingual transfer. |
| Outcome: | The proposed model can achieve good performance even if representations of different languages are not aligned well. |
Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference (2025.acl-long)
Copied to clipboard
Benjamin Warner, Antoine Chaffin, Benjamin Clavié, Orion Weller, Oskar Hallström, Said Taghadouini, Alexis Gallagher, Raja Biswas, Faisal Ladhak, Tom Aarsen, Griffin Thomas Adams, Jeremy Howard, Iacopo Poli
| Challenge: | Encoder-only transformer models such as BERT offer a great performance-size tradeoff for retrieval and classification tasks compared to larger decoder models. |
| Approach: | They introduce a new transformer model, ModernBERT, which brings modern model optimizations to encoder-only transformer models. |
| Outcome: | The proposed model improves on the BERT transformer model and is faster and more memory efficient than the older models. |
HintedBT: Augmenting Back-Translation with Quality and Transliteration Hints (2021.emnlp-main)
Copied to clipboard
| Challenge: | HintedBT provides hints (as source tags on the encoder) about the quality of each source-target pair. |
| Approach: | They propose a method which provides hints to the encoder and decoder to improve the quality of BT data by providing hints about the quality. |
| Outcome: | The proposed method improves translation quality and performance in three low/medium-resource language pairs. |
Normal-Abnormal Decoupling Memory for Medical Report Generation (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for capturing nuanced visual information are prone to data bias and noise. |
| Approach: | They propose a normal-abnormal semantic decoupling network that utilizes abnormal pattern memory to optimize visual extraction through the extraction of abnormal semantics from the reports. |
| Outcome: | The proposed approach surpasses the current state-of-the-art methods on the benchmark MIMIC-CXR and shows excellent performance on the same dataset. |
Two are Better than One: Joint Entity and Relation Extraction with Table-Sequence Encoders (2020.emnlp-main)
Copied to clipboard
| Challenge: | Named entity recognition and relation extraction are two important fundamental problems. |
| Approach: | They propose to design two separate encoders to capture two different types of information in the representation learning process. |
| Outcome: | The proposed methods show significant improvements on standard datasets. |
When do Contrastive Word Alignments Improve Many-to-many Neural Machine Translation? (2022.findings-naacl)
Copied to clipboard
| Challenge: | Existing methods to improve pre-training for many-to-many neural machine translation use manual cleaning of bilingual dictionaries, which are unavailable for most language pairs. |
| Approach: | They propose a word-level contrastive objective to leverage word alignments for many-to-many neural machine translation (NMT) Empirical results show that this leads to 0.8 BLEU gains for several language pairs. |
| Outcome: | Empirical results show that the proposed objective leads to 0.8 BLEU gains for several language pairs. |
A Query-Parallel Machine Reading Comprehension Framework for Low-resource NER (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Named entity recognition (NER) is a fundamental task in natural language processing. |
| Approach: | They propose a query-parallel MRC-based approach to named entity recognition . the model is trained with parameter-efficient tuning technique, making it more data-efficient . |
| Outcome: | The proposed model performs competitively against strong baseline methods in resource-rich settings and achieves state-of-the-art results in low-resource settings. |
Pseudo-Bidirectional Decoding for Local Sequence Transduction (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Local sequence transduction tasks involve massive overlapping between source and target sequences . experimental results show that Pseudo-Bidirectional Decoding improves performance of standard seq2seq models. |
| Approach: | They propose a simple but versatile approach for local sequence transduction tasks . they propose to copy source tokens to decoder as pseudo future context . |
| Outcome: | The proposed approach improves the performance of standard seq2seq models on LST tasks. |
A Semantic Mention Graph Augmented Model for Document-Level Event Argument Extraction (2024.lrec-main)
Copied to clipboard
| Challenge: | Document-level Event Argument Extraction (DEAE) aims to identify arguments and their specific roles from unstructured document. |
| Approach: | They propose a document-prompt-based method for document-level event argument extraction that uses a semantic mention graph to capture relations between documents and prompts. |
| Outcome: | The proposed method surpasses baseline methods and achieves state-of-the-art performance on RAMS and WikiEvents datasets. |
Probing Linguistic Features of Sentence-Level Representations in Neural Relation Extraction (2020.acl-main)
Copied to clipboard
| Challenge: | Neural relation extraction models capture linguistic and semantic properties of the input, a recent study shows. |
| Approach: | They introduce 14 probing tasks targeting linguistic properties relevant to RE . they add contextualized word representations to enhance probing performance . |
| Outcome: | The proposed models achieve state-of-the-art on two datasets, TACRED and SemEval 2010 Task 8 . they show that the models capture linguistic and semantic properties relevant to the downstream task . |
Accurate and Well-Calibrated ICD Code Assignment Through Attention Over Diverse Label Embeddings (2024.eacl-long)
Copied to clipboard
| Challenge: | Existing approaches to assigning ICD codes to clinical text are time-consuming, labor intensive, and error-prone. |
| Approach: | They propose to adapt a Transformer-based model to a longformer model and use it to encode clinical narratives. |
| Outcome: | The proposed approach outperforms current state-of-the-art models in ICD coding with the label embeddings contributing to the good performance. |
Unsupervised Relation Extraction: A Variational Autoencoder Approach (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for relation extraction use latent variables and supervised training which requires large datasets. |
| Approach: | They propose a VAE-based unsupervised relation extraction technique that uses latent variables as an intermediate variable instead of a latent variable. |
| Outcome: | The proposed method outperforms state-of-the-art methods on the NYT dataset and outperformed existing methods. |
Improving Relation Extraction through Syntax-induced Pre-training with Dependency Masking (2022.findings-acl)
Copied to clipboard
| Challenge: | Existing studies require modifications to existing baseline architectures to leverage syntactic information. |
| Approach: | They propose to leverage syntactic information to improve relation extraction by training a syntax-induced encoder on auto-parsed data through dependency masking. |
| Outcome: | The proposed approach outperforms baseline models and achieves state-of-the-art results on two English datasets. |
Enhancing Neural Machine Translation with Semantic Units (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods to model and leverage semantic units in natural language do not provide a complete understanding of the whole sentence. |
| Approach: | They propose a method which models the integral meanings of semantic units within a sentence . they propose 'word pair encoder' to help identify the boundaries of semantic unit boundaries . |
| Outcome: | The proposed method outperforms baselines and supports the semantic unit representation of subwords and tokens. |
Product Description and QA Assisted Self-Supervised Opinion Summarization (2024.findings-naacl)
Copied to clipboard
Tejpalsingh Siledar, Rupasai Rangaraju, Sankara Muddu, Suman Banerjee, Amey Patil, Sudhanshu Singh, Muthusamy Chelliah, Nikesh Garera, Swaprava Nath, Pushpak Bhattacharyya
| Challenge: | Existing methods to generate opinion summarization without supervised training data are limited due to the lack of additional sources. |
| Approach: | They propose a synthetic dataset creation strategy that leverages reviews and additional sources to generate a pseudo-summary. |
| Outcome: | The proposed approach achieves 14.5% improvement in ROUGE-1 F1 over existing models. |
Deep Communicating Agents for Abstractive Summarization (N18-1)
Copied to clipboard
| Challenge: | Empirical results show that multiple communicating agents produce a better summary than extractive summarization. |
| Approach: | They propose an encoder-decoder architecture that uses deep communicating agents to represent a long document for abstractive summarization. |
| Outcome: | Empirical results show that multiple communicating agents produce a better summary than baselines. |
GTR-LSTM: A Triple Encoder for Sentence Generation from RDF Data (P18-1)
Copied to clipboard
| Challenge: | Knowledge bases are becoming an enabling resource for many applications including Q&A systems, recommender systems, and summarization tools. |
| Approach: | They propose a system to translate RDF triples into natural sentences using an encoder-decoder framework. |
| Outcome: | The proposed model outperforms the baseline model by 17.6%, 6.0%, and 16.4% in terms of BLEU, METEOR, and TER scores. |
African or European Swallow? Benchmarking Large Vision-Language Models for Fine-Grained Object Classification (2024.emnlp-main)
Copied to clipboard
| Challenge: | Recent Large Vision Language Models demonstrate impressive abilities on image understanding and reasoning tasks. |
| Approach: | They propose a benchmark for fine-grained object classification that is difficult to evaluate . they benchmark 12 public LVLMs on and show CLIP models exhibit better performance . |
| Outcome: | The proposed model improves on 12 public LVLMs on image understanding and reasoning tasks. |
Label Semantics for Few Shot Named Entity Recognition (2022.findings-acl)
Copied to clipboard
Jie Ma, Miguel Ballesteros, Srikanth Doss, Rishita Anubhai, Sunil Mallya, Yaser Al-Onaizan, Dan Roth
| Challenge: | Named entity recognition (NER) is a fundamental natural language understanding task that requires large amounts of high quality annotated in-domain data. |
| Approach: | They propose a neural architecture that leverages the semantic information in the names of the labels to give the model additional signal and enriched priors. |
| Outcome: | The proposed model is especially effective in low resource settings. |
Task-Aware Specialization for Efficient and Robust Dense Retrieval for Open-Domain Question Answering (2023.acl-short)
Copied to clipboard
| Challenge: | Existing dense retrieval models are parameter-inefficient and underperform sparse counterparts. |
| Approach: | They propose a task-aware specialization for dEnse Retrieval architecture that enables parameter sharing by interleaving shared and specialized blocks in a single encoder. |
| Outcome: | The proposed architecture surpasses BM25 on questions and passages using 60% of the parameters as bi-encoder dense retrievers. |
What’s This Movie About? A Joint Neural Network Architecture for Movie Content Analysis (N18-1)
Copied to clipboard
| Challenge: | Using movie overviews, we can gain a general impression of a movie by summarizing its content, genre, and artistic style. |
| Approach: | They propose a novel end-to-end model that generates movie overviews from an online database and a multi-label encoder for identifying screenplay attributes. |
| Outcome: | The proposed model reliably assigns good labels for movie attributes and generates sentences conditioned on the identified attributes. |
Do Neural Topic Models Really Need Dropout? Analysis of the Effect of Dropout in Topic Modeling (2023.eacl-main)
Copied to clipboard
| Challenge: | Dropout is a regularization trick used to resolve overfitting in large feedforward neural networks, but there is nil analysis of it for unsupervised models and in particular, VAE-based neural topic models. |
| Approach: | They propose to use dropout to solve overfitting problems in unsupervised neural topic models by stochastically dropping out the activation of neurons to prevent complex co-adaptations of feature vectors. |
| Outcome: | The proposed class of neural topic models can be used to improve the quality and predictive performance of the generated topics. |
Efficient CTC Regularization via Coarse Labels for End-to-End Speech Translation (2023.eacl-main)
Copied to clipboard
| Challenge: | Developing techniques to support end-to-end speech translation is non-trivial because of the speech-text modality gap. |
| Approach: | They propose a coarse labeling approach that merges vocabulary labels via simple heuristic rules . they propose to use 256-bit truncation, division or modulo operations to regularize the encoder . |
| Outcome: | The proposed method can increase training efficiency while delivering better performance. |
Investigating Multilingual NMT Representations at Scale (D19-1)
Copied to clipboard
| Challenge: | Multilingual Neural Machine Translation models have shown success in transfer learning settings, but their mode of transfer remains elusive. |
| Approach: | They propose to use a representation similarity framework to compare multilingual representations using a SVCCA representation similar to the previous work. |
| Outcome: | The proposed model can be used to compare representations across languages and layers. |
Automatic Data Visualization Generation from Chinese Natural Language Questions (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing studies on data visualization generation from natural languages have not been conducted on Chinese Text-to-Vis. |
| Approach: | They propose to generate a Chinese text-to-vis dataset using a multilingual encoder and a cross-lingual ability. |
| Outcome: | The proposed dataset is challenging and deserves further research. |
RSGT: Relational Structure Guided Temporal Relation Extraction (2022.coling-1)
Copied to clipboard
| Challenge: | Temporal relation extraction (TRE) is crucial for natural language understanding. |
| Approach: | They propose a Temporal Relational Structure Guided Temporal Relations Extraction task to extract relational structure features that can fit for both inter-sentence and intra-sentent relations. |
| Outcome: | The proposed method improves on two well-known datasets, MATRES and TB-Dense, and can be used for clinical diagnosis and summarization. |
Neural Machine Translation with Reordering Embeddings (P19-1)
Copied to clipboard
| Challenge: | Existing work exploits the reordering information in neural machine translation . experimental results show that the proposed methods can significantly improve the performance of the transformer translation system. |
| Approach: | They propose a reordering mechanism to learn the re ordering embedding of a word based on contextual information and stack them together with self-attention networks to learn sentence representation for machine translation. |
| Outcome: | The proposed method improves translation performance on English-to-German, NIST Chinese-to English, and WAT Japanese-toEnglish translation tasks. |
Exploring Cross-Lingual Transfer Learning with Unsupervised Machine Translation (2021.findings-acl)
Copied to clipboard
| Challenge: | a new CLTL model is proposed to facilitate cross-linguistic transfer learning between distant languages . a key to CLTL is to learn a shared representation space for the given source-target language pair. |
| Approach: | They propose a new CLTL model that integrates machine translation with MT . they use an unannotated data technique to make use of the model's pre-training and fine-tuning . |
| Outcome: | The proposed model achieves better CLTL performance than the baseline model without more annotated data. |
RED-ACE: Robust Error Detection for ASR using Confidence Embeddings (2022.emnlp-main)
Copied to clipboard
| Challenge: | ASR Error Detection (AED) models post-process the output of Automatic Speech Recognition systems, in order to detect transcription errors. |
| Approach: | They propose to use ASR model's word-level confidence scores to combine ASR models with transcribed text to improve AED performance. |
| Outcome: | The proposed models combine the confidence scores and transcribed text into a contextualized representation. |
Fast-R2D2: A Pretrained Recursive Neural Network based on Pruned CKY for Grammar Induction and Text Representation (2022.emnlp-main)
Copied to clipboard
| Challenge: | Chart-based models have shown great potential in unsupervised grammar induction, running recursively and hierarchically, but requiring O(n3) time-complexity. |
| Approach: | They propose a model-guided pruning method that scales to large language model pretraining by introducing a heuristic pruning method. |
| Outcome: | The proposed method significantly improves grammar induction quality and achieves competitive results in downstream tasks. |
Beyond Coherence: Improving Temporal Consistency and Interpretability in Dynamic Topic Models (2026.findings-eacl)
Copied to clipboard
| Challenge: | Existing topic models capture bag-of-words statistics but lack semantic priors . interpretability remains shallow, relying on noisy top-word lists that obscure thematic clarity. |
| Approach: | They propose a variational framework to capture more faithful temporal trajectories . they propose to use entropy-regularized optimal transport to align entire topic constellations . |
| Outcome: | The proposed framework captures more faithful temporal trajectories and improves interpretability. |
First Align, then Predict: Understanding the Cross-Lingual Ability of Multilingual BERT (2021.eacl-main)
Copied to clipboard
| Challenge: | Multilingual pretrained language models have demonstrated remarkable zero-shot cross-lingual transfer capabilities. |
| Approach: | They propose to use a layer ablation technique to create a multilingual model that is viewed as a stacking of two sub-networks: a language-agnostic encoder and a task-specific predictor. |
| Outcome: | The proposed model can perform zero-shot cross-lingual transfer for many languages. |
Rhetorically Controlled Encoder-Decoder for Modern Chinese Poetry Generation (P19-1)
Copied to clipboard
| Challenge: | Rhetoric is a vital element in modern Chinese poetry, and plays an essential role in improving its aesthetics. however, to date, it has not been considered in research on automatic poetry generation. |
| Approach: | They propose a rhetorically controlled encoder-decoder for modern Chinese poetry generation . their model captures various rhetorical patterns in an encoder and incorporates mixtures . |
| Outcome: | The proposed model outperforms state-of-the-art methods in terms of fluency, coherence, meaningfulness, and rhetorical aesthetics. |
CKDST: Comprehensively and Effectively Distill Knowledge from Machine Translation to End-to-End Speech Translation (2023.findings-acl)
Copied to clipboard
| Challenge: | End-to-end speech-totext translation (ST) data are limited due to the limited resources. |
| Approach: | They propose a knowledge distillation framework for speech translation that integrates knowledge from machine translation and decouples knowledge from non-target class knowledge. |
| Outcome: | The proposed framework outperforms state-of-the-art models on a benchmark dataset. |
Zero-Shot Event Detection Based on Ordered Contrastive Learning and Prompt-Based Prediction (2022.findings-naacl)
Copied to clipboard
| Challenge: | Existing zero-shot event detection methods do not work for unseen types . supervised methods require predefined event types or external tools . |
| Approach: | They propose a framework to detect events from unstructured text without annotating samples . they propose to use ordered contrastive learning and prompt-based prediction to identify trigger words . |
| Outcome: | The proposed model detects events more effectively and accurately than state-of-the-art methods. |
ConveRT: Efficient and Accurate Conversational Representations from Transformers (2020.findings-emnlp)
Copied to clipboard
| Challenge: | ConveRT is a pretraining framework for conversational AI that is computationally heavy, slow, and expensive to train. |
| Approach: | They propose a pretraining framework for conversational tasks that is efficient, lightweight, and inexpensive. |
| Outcome: | The proposed model achieves state-of-the-art performance across widely established responses . it trains substantially faster than existing state- of-the art models . |
LGESQL: Line Graph Enhanced Text-to-SQL Model with Mixed Local and Non-Local Relations (2021.acl-long)
Copied to clipboard
| Challenge: | Existing methods to encode text-to-SQL data are node-centric and ignore semantics embedded in the topological structure of edges. |
| Approach: | They propose a Line Graph Enhanced Text-to-SQL model to mine relational features without constructing meta-paths. |
| Outcome: | The proposed model achieves state-of-the-art on the cross-domain text-to-SQL benchmark Spider at the time of writing. |
Stacked Acoustic-and-Textual Encoding: Integrating the Pre-trained Models into Speech Translation Encoders (2021.acl-long)
Copied to clipboard
| Challenge: | End-to-end Speech Translation (E2E ST) encoders lack global context representation, whereas MT encoder lacks it. |
| Approach: | They propose a Stacked Acoustic-and-Textual Encoding method for speech translation . they propose an adaptor module to alleviate representation inconsistency . |
| Outcome: | The proposed method achieves state-of-the-art BLEU scores of 18.3 and 25.2 on two ST tasks. |
Improving Abstractive Document Summarization with Salient Information Modeling (P19-1)
Copied to clipboard
| Challenge: | Abstractive document summarization is a task of natural language generation which generates fluent summaries with salient information automatically. |
| Approach: | They propose to incorporate a Gaussian focal bias on attention scores into an encoder to enhance the perception of local context and to distinguish salient information precisely. |
| Outcome: | The proposed framework outperforms state-of-the-art models on the CNN/Daily Mail benchmark and is based on a focus-attention mechanism and two new extensions. |
A Semi-supervised Approach to Generate the Code-Mixed Text using Pre-trained Encoder and Transfer Learning (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods to train neural network-based models for code-mixing are limited due to language specificity of code-mixed text. |
| Approach: | They propose a deep learning approach to generate code-mixed text from English to multiple languages without any parallel data. |
| Outcome: | The proposed approach generates a code-mixed text from English to multiple languages without any parallel data. |
CSP:Code-Switching Pre-training for Neural Machine Translation (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods to train neural machine translation models are data-hungry and low-resource . et al., 2018; Radford e.t., 2019; Yang ee.,2019) proposes a new pre-training method for NMT . |
| Approach: | They propose a new pre-training method which randomly replaces some words in the input sentence with their translation words in target language. |
| Outcome: | The proposed method improves on unsupervised and supervised NMT models by making full use of monolingual corpora. |
Breaking Down Multilingual Machine Translation (2022.findings-acl)
Copied to clipboard
| Challenge: | Multilingual training is an essential ingredient in machine translation systems . but it has different effects in different multilingual settings, such as many-to-one, one-tomany and many- to-many learning . |
| Approach: | They compare multilingual training settings with encoders and decoders initialized by multilingual learning . they find important attention heads for each language pair and compare their correlations during inference . |
| Outcome: | The proposed models outperform the best models for high-resource languages and one-to-many models for low-resourced languages. |
Less is More: Pretrain a Strong Siamese Encoder for Dense Text Retrieval Using a Weak Decoder (2021.emnlp-main)
Copied to clipboard
Shuqi Lu, Di He, Chenyan Xiong, Guolin Ke, Waleed Malik, Zhicheng Dou, Paul Bennett, Tie-Yan Liu, Arnold Overwijk
| Challenge: | Dense retrieval requires high-quality text sequence embeddings to support effective search in the representation space. |
| Approach: | They propose a self-learning method that pre-trains the autoencoder using a weak decoder to push the encoder to provide better sequence representations. |
| Outcome: | The proposed model significantly boosts the effectiveness and few-shot ability of dense retrieval models on web search, news recommendation, and open domain question answering. |
AdaST: Dynamically Adapting Encoder States in the Decoder for End-to-End Speech-to-Text Translation (2021.findings-acl)
Copied to clipboard
| Challenge: | End-to-end speech translation models learn acoustic representations from the encoder, which is not desirable for cross-modal and cross-lingual translation. |
| Approach: | They propose an adaptive speech-to-text translation model that dynamically adapts acoustic states in the decoder. |
| Outcome: | The proposed model outperforms state-of-the-art speech translation models on two widely-used datasets. |
Semi-Supervised Dependency Parsing with Arc-Factored Variational Autoencoding (2020.coling-main)
Copied to clipboard
| Challenge: | Existing methods for dependency parsing use unlabelled data to compensate for the lack of training corpora. |
| Approach: | They propose semi-supervised dependency parsing methods that utilize unlabelled data to compensate for the scarcity of labelled training corpora. |
| Outcome: | The proposed model overcomes the tree constraint and the complexity of the training procedure while avoiding the challenges brought by the tree constraints. |
Ruleformer: Context-aware Rule Mining over Knowledge Graph (2022.coling-1)
Copied to clipboard
| Challenge: | Existing work on rule mining focuses on mining rules, but how to select appropriate rules for completion of different triplets has not been discussed. |
| Approach: | They propose to take context information into consideration when selecting suitable rules . they devise a transformer-based rule mining approach, Ruleformer . |
| Outcome: | The proposed model takes context information into consideration, which helps select suitable rules for inference tasks. |
Learning Semantic Sentence Embeddings using Sequential Pair-wise Discriminator (C18-1)
Copied to clipboard
| Challenge: | a novel method for obtaining sentence-level embeddings is proposed . the problem of obtaining a semantic embeddable sentence is at the core of understanding languages . |
| Approach: | They propose a method for obtaining sentence-level embeddings by using a sequential encoder-decoder framework. |
| Outcome: | The proposed method outperforms the state-of-the-art on a sentiment analysis task. |
Multilingual Translation via Grafting Pre-trained Language Models (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods to graft pre-trained (masked) language models to multilingual data are limited, and they lack cross-attention component. |
| Approach: | They propose to graft separately pre-trained (masked) language models for machine translation using monolingual data and parallel data. |
| Outcome: | The proposed method achieves average improvements of 5.8 BLEU in x2en and 2.9 BLUE in en2x directions compared with the multilingual Transformer of the same size. |
Extracting and Encoding: Leveraging Large Language Models and Medical Knowledge to Enhance Radiological Text Representation (2024.findings-acl)
Copied to clipboard
| Challenge: | Advancing representation learning in specialized fields like medicine remains challenging due to the scarcity of expert annotations for text and images. |
| Approach: | They propose a Fact Extractor that leverages large language models to extract factual statements from radiology reports. |
| Outcome: | The proposed framework outperforms current state-of-the-art methods in sentence ranking, natural language inference, and label extraction tasks. |
Example-Driven Intent Prediction with Observers (2021.naacl-main)
Copied to clipboard
| Challenge: | Prior work has shown that BERT-like models attribute a significant amount of attention to the [CLS] token, which results in diluted representations. |
| Approach: | They propose two approaches to improve generalizability of dialog system intent classification models by using observers and example-driven training. |
| Outcome: | The proposed models achieve state-of-the-art on three intent prediction datasets in both the full data and few-shot settings. |
Multi-Granular Sequence Encoding via Dilated Compositional Units for Reading Comprehension (D18-1)
Copied to clipboard
| Challenge: | Sequence encoders are crucial components in many neural architectures for learning to read and comprehend. |
| Approach: | They propose a compositional encoder that explicitly models across multiple granularities using a new dilated composition mechanism. |
| Outcome: | The proposed encoder is fast and expressive, and can model across multiple granularities. |
Quantifying Context Mixing in Transformers (2023.eacl-main)
Copied to clipboard
| Challenge: | Self-attention weights and their transformed variants have been used for analyzing token-to-token interactions in Transformer-based models, but they are not faithful to the models’ decisions as they are only one part of an encoder block. |
| Approach: | They propose a new context mixing score customized for Transformers that provides us with a deeper understanding of how information is mixed at each encoder layer. |
| Outcome: | The proposed score outperforms other methods in linguistically informed rationales, probing, and faithfulness analysis. |
Constituency Parsing with a Self-Attentive Encoder (P18-1)
Copied to clipboard
| Challenge: | Recent work on LSTM encoders based on recurrent neural networks has led to improvements in constituency parsing accuracy. |
| Approach: | They propose to replace an LSTM encoder with a self-attentive architecture to improve a discriminative constituency parser. |
| Outcome: | The proposed model outperforms the previous best-published results on 8 of the 9 languages in the SPMRL dataset. |
Knowledge-enriched, Type-constrained and Grammar-guided Question Generation over Knowledge Bases (2020.coling-main)
Copied to clipboard
| Challenge: | Existing methods for question generation over knowledge bases have low diversity and poor fluency due to the limited information contained in the subgraphs and semantic drift due to decoder’s oblivion of the semantics of the answer entity. |
| Approach: | They propose a knowledge-enriched, type-constrained and grammar-guided KBQG model that generates natural-language questions over a set of triples in the KB. |
| Outcome: | The proposed model outperforms existing methods on two widely-used benchmark datasets. |
Modelling Context Emotions using Multi-task Learning for Emotion Controlled Dialog Generation (2021.eacl-main)
Copied to clipboard
| Challenge: | Recent research has tackled this task using neural generative methods by augmenting emotion classes with the input sequences. |
| Approach: | They propose to use a self-attention based encoder and a decoder with dot product attention mechanism to generate a viable response with a specified emotion. |
| Outcome: | The proposed model outperforms baselines on automatic evaluation measures such as F1 and BLEU scores, thus resulting in more fluent and adequate responses. |
On Sparsifying Encoder Outputs in Sequence-to-Sequence Models (2021.findings-acl)
Copied to clipboard
| Challenge: | Using sequence-to-sequence models, encoder outputs are usually transferred to the decoder for generation, but in this study, encoded outputs can be compressed to shorten the sequence for decoding. |
| Approach: | They propose to use a stochastic gate-based algorithm to mask encoder outputs to shorten the sequence delivered for decoding. |
| Outcome: | The proposed model can be used to shorten encoder outputs to short a sequence . the proposed model yields a speedup of up to 1.65 on document summarization and 1.20 on character-based machine translation tasks. |
Adaptive Weighting for Neural Machine Translation (C18-1)
Copied to clipboard
| Challenge: | Existing weighted sum models (WSMs) take inputs and generate one output, but they are independent of each other and are fixed for all inputs. |
| Approach: | They propose adaptive weighting for WSMs to control the contribution of each input and output state. |
| Outcome: | The proposed weighting improves translation accuracy by 1.49 and 0.92 BLEU points on Chinese-to-English translation and English-to German translation tasks. |
DeltaNet: Conditional Medical Report Generation for COVID-19 Diagnosis (2022.coling-1)
Copied to clipboard
Xian Wu, Shuxin Yang, Zhaopeng Qiu, Shen Ge, Yangtian Yan, Xingwang Wu, Yefeng Zheng, S. Kevin Zhou, Li Xiao
| Challenge: | X-ray and CT are the gold standard for COVID-19 diagnosis and treatment . however, due to the excessive number of patients, writing reports becomes a heavy burden for radiologists. |
| Approach: | They propose to use X-ray and CT to generate medical reports automatically . they evaluate DeltaNet on a COVID-19 dataset, where it outperforms state-of-the-art approaches . |
| Outcome: | The proposed system outperforms state-of-the-art methods on a COVID-19 dataset. |
End to End Chinese Lexical Fusion Recognition with Sememe Knowledge (2020.coling-main)
Copied to clipboard
| Challenge: | a new task for coreference recognition is presented in linguistics . the fusion word is always out-of-vocabulary (OOV) words in downstream paragraph-level tasks . |
| Approach: | They propose a Chinese lexical fusion recognition task which could be regarded as one kind of coreference recognition. |
| Outcome: | The proposed model is effective and competitive for the proposed task. |
Language Tags Matter for Zero-Shot Neural Machine Translation (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing studies on multilingual machine translation have ignored the importance of LTs. |
| Approach: | They propose to use language tag (LT) strategies to indicate translation directions in MNMT to enhance consistency and alleviate off-target issues in zero-shot directions. |
| Outcome: | The proposed model could translate between unsupervised languages and achieve a +8 BLEU score difference over other LT strategies in translation tasks. |
Retrieval-augmented Image Captioning (2023.eacl-main)
Copied to clipboard
| Challenge: | Experimental results show that image captioning can be effectively formulated from this new perspective. |
| Approach: | They propose a pretrained visual and language decoders for image captioning that generate sentences from the input image and a set of captions retrieved from a datastore. |
| Outcome: | The proposed model generates sentences given the input image and retrieved captions, while the decoder attends to the multimodal encoder representations. |
Beyond the Scientific Document: A Citation-Aware Multi-Granular Summarization Approach with Heterogeneous Graphs (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Experimental results demonstrate that our model outperforms existing approaches for summarizing documents. |
| Approach: | proposed model constructs a heterogeneous graph to represent a document and its relevant external citations. |
| Outcome: | The proposed model outperforms existing models in three different scenarios. |
General Purpose Text Embeddings from Pre-trained Language Models for Scalable Inference (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Large pre-trained language models are currently used for many NLP tasks . however, inference for these models requires significant computational resources . |
| Approach: | They propose to use a shared text encoder to amortize the computational cost of inference over multiple tasks. |
| Outcome: | The proposed method reduces the size of the extracted representations by a factor of 16 to store them for later use. |
Semantically-Aligned Equation Generation for Solving and Reasoning Math Word Problems (N19-1)
Copied to clipboard
| Challenge: | Existing methods to solve math word problems require accurate natural language understanding to bridge texts and math expressions. |
| Approach: | They propose a neural approach to automatically solve math word problems by operating symbols according to their semantic meanings in texts. |
| Outcome: | The proposed model outperforms state-of-the-art models and the best non-retrieval-based models over 10% accuracy in a Math23K dataset. |
A Novel Graph-based Multi-modal Fusion Encoder for Neural Machine Translation (2020.acl-main)
Copied to clipboard
| Challenge: | Existing multi-modal neural machine translation models do not fully exploit fine-grained semantic correspondences between semantic units of different modalities. |
| Approach: | They propose a graph-based multi-modal fusion encoder that exploits fine-grained semantic correspondences between different modalities. |
| Outcome: | The proposed encoder significantly extends the conventional text-based translation by taking images as additional inputs. |
Neural Machine Translation Incorporating Named Entity (C18-1)
Copied to clipboard
| Challenge: | Conventional NMT models have difficulty translating words with multiple meanings because of the high ambiguity. |
| Approach: | They propose a neural machine translation model that incorporates named entity (NE) tags of source-language sentences to reduce the difficulty in translating multiple meanings. |
| Outcome: | The proposed model achieves 3.11 point improvement in bilingual evaluation understudy (BLEU) on English-to-Japanese translation task with the ASPEC, and English- to-Bulgarian and English to-Romanian translation tasks with the Europarl corpus. |
Z-Code++: A Pre-trained Language Model Optimized for Abstractive Summarization (2023.acl-long)
Copied to clipboard
Pengcheng He, Baolin Peng, Song Wang, Yang Liu, Ruochen Xu, Hany Hassan, Yu Shi, Chenguang Zhu, Wayne Xiong, Michael Zeng, Jianfeng Gao, Xuedong Huang
| Challenge: | Z-Code++ is a pre-trained language model optimized for abstractive text summarization. |
| Approach: | They propose a pre-trained language model optimized for abstractive text summarization that uses a two-phase pre-training technique to improve model's performance. |
| Outcome: | The proposed model outperforms the competing models on low-resource summarization tasks in zero-shot and few-shot settings. |
Disentangled Sequence to Sequence Learning for Compositional Generalization (2022.acl-long)
Copied to clipboard
| Challenge: | Existing models struggle to generalize to unseen compositions of seen components . a new approach allows for disentangled representations and better generalization . |
| Approach: | They propose an extension to sequence-to-sequence models which encourage disentanglement by re-encoding source input. |
| Outcome: | The proposed extension delivers better generalization and more disentangled representations . human expressions can be understood by combining known atomic components . |
Multilingual Unsupervised NMT using Shared Encoder and Language-Specific Decoders (P19-1)
Copied to clipboard
| Challenge: | Existing approaches to train multiple languages with a shared encoder and multiple decoders are based on denoising autoencoding of each language and back-translating between English and multiple non-English languages. |
| Approach: | They propose a multilingual unsupervised NMT scheme which trains multiple languages with a shared encoder and multiple decoders. |
| Outcome: | The proposed model performs better than the separately trained bilingual models on monolingual corpora and improves by 1.48 BLEU points on WMT test sets. |
Recipes for Adapting Pre-trained Monolingual and Multilingual Models to Machine Translation (2021.eacl-main)
Copied to clipboard
| Challenge: | Recent advances in machine translation (MT) have improved performance on low-resource language pairs. |
| Approach: | They propose to freeze most BART parameters and add new ones to fine-tune a model trained on MT. |
| Outcome: | The proposed model outperforms naive fine-tuning on Vietnamese to English on a training set for Vietnamese to Vietnamese . the proposed model is able to fine- tune on smaller datasets while still maintaining the same model performance. |
MMNMT: Modularizing Multilingual Neural Machine Translation with Flexibly Assembled MoE and Dense Blocks (2023.emnlp-main)
Copied to clipboard
| Challenge: | Mixture-of-Experts (MoE) based sparse architectures are prone to overfitting on low-resource language translation. |
| Approach: | They propose a modularized MNMT framework that flexibly assembles dense and MoE-based sparse modules to achieve the best of both worlds. |
| Outcome: | The proposed framework outperforms existing models on low-resource language translation and zero-shot translation on benchmark datasets. |
Improved Visual Story Generation with Adaptive Context Modeling (2023.findings-acl)
Copied to clipboard
| Challenge: | a recent work shows that diffusion models generate images of high resolution and semantic consistency to text prompts. |
| Approach: | They propose a method that uses adaptive context modeling to improve leading system . they evaluate their method on pororoSV and FlintstonesSV datasets . |
| Outcome: | The proposed method achieves state-of-the-art FID scores on pororo and Flintstones datasets. |
Scented-EAE: Stage-Customized Entity Type Embedding for Event Argument Extraction (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for incorporating entities into EAE rely on prompts or NER . weak semantic associations due to missing role-entity correspondence cues . one-sided semantic understanding relying solely on argument role semantics a problem . |
| Approach: | They propose an EAE model with stage-customized entity type embedding to explore the role of entity types. |
| Outcome: | The proposed model achieves state-of-the-art performance on mainstream benchmarks and robustness in low-resource settings. |
Federated Learning for Spoken Language Understanding (2020.coling-main)
Copied to clipboard
| Challenge: | Existing methods to improve robustness of models focus on a single dataset . but, there are few studies on how to combine merits of different datasets . |
| Approach: | They propose a federated learning framework that could unify datasets and tasks . they propose MV-Encoder as backbone of the framework to provide multi-granularity text representations . |
| Outcome: | The proposed framework improves on two SLU benchmark datasets and federated learning settings. |
Improving Domain Adaptation Translation with Domain Invariant and Specific Information (N19-1)
Copied to clipboard
| Challenge: | Neural machine translation models are based on the encoder-decoder architecture, which makes them overfitting to frequent observations. |
| Approach: | They propose a method to explicitly model out-of-domain information in an encoder-decoder framework . they propose combining out- of-domain training data with out-out-of domain data . |
| Outcome: | The proposed method outperforms baselines on multiple data sets. |
RepCodec: A Speech Representation Codec for Speech Tokenization (2024.acl-long)
Copied to clipboard
| Challenge: | Recent advances in large language models have led to discrete speech tokenization, but this discretization can be costly and impedes performance. |
| Approach: | They propose a new speech representation codec for semantic speech tokenization that reconstructs speech representations from speech encoders like HuBERT or data2vec. |
| Outcome: | The proposed method outperforms the widely used k-means clustering approach in speech understanding and generation. |
Attention Is All You Need for Chinese Word Segmentation (2020.emnlp-main)
Copied to clipboard
| Challenge: | Recent work on Chinese word segmentation has been concerned about the following three perspectives. |
| Approach: | They propose to use a greedy decoding algorithm to improve Chinese word segmentation model. |
| Outcome: | The proposed model achieves state-of-the-art or comparable performance against strong baselines in strict closed test setting. |
Graph Enhanced Contrastive Learning for Radiology Findings Summarization (2022.acl-long)
Copied to clipboard
| Challenge: | Existing methods for automating impression generation have limited the relationship between extra knowledge and the original findings. |
| Approach: | They propose a framework for automating impression generation that exploits extra knowledge and original findings . they propose combining key words and their relations to extract critical information . |
| Outcome: | The proposed framework exploits extra knowledge and the original findings in an integrated way . the state-of-the-art results on two datasets confirm the effectiveness of the proposed method . |
A Simple and Effective Unified Encoder for Document-Level Machine Translation (2020.acl-main)
Copied to clipboard
| Challenge: | Existing models for document-level machine translation use two separate encoders to model the source sentences and document- level contexts. |
| Approach: | They propose a unified encoder that can outperform existing models of dual-encoder models . they propose to use document-level contexts to model the interaction between the contexts and the source sentences . |
| Outcome: | The proposed model outperforms baseline models of dual-encoder models in terms of BLEU and METEOR scores. |
Knowledge Distillation for Multilingual Unsupervised Neural Machine Translation (2020.acl-main)
Copied to clipboard
| Challenge: | Unsupervised neural machine translation (UNMT) can only translate between a single language pair and cannot produce translation results for multiple language pairs at the same time. |
| Approach: | They propose a method to translate between 13 languages using a single encoder and a decoder . they propose two knowledge distillation methods to further enhance multilingual UNMT performance . |
| Outcome: | The proposed method improves translation performance for all languages using multilingual data. |
Transformer-based Lexically Constrained Headline Generation (2021.emnlp-main)
Copied to clipboard
Kosuke Yamada, Yuta Hitomi, Hideaki Tamori, Ryohei Sasano, Naoaki Okazaki, Kentaro Inui, Koichi Takeda
| Challenge: | Existing automatic headline generation methods cannot include a given phrase in the generated headline. |
| Approach: | They propose a Transformer-based method that guarantees to include a given phrase in a generated headline. |
| Outcome: | The proposed method achieves ROUGE scores comparable to previous methods with Japanese news corpus. |
Packed Levitated Marker for Entity and Relation Extraction (2022.acl-long)
Copied to clipboard
| Challenge: | Existing work on entity and relation extraction ignores the interrelation between spans . a novel approach to extract better span representations from pre-trained languages is needed . |
| Approach: | They propose a span representation approach that packs Levitated Markers to consider interrelation between spans. |
| Outcome: | The proposed model improves on baselines on six NER benchmarks and achieves a 4.1%-4.3% strict relation F1 improvement with higher speed over previous state-of-the-art models. |
Multi-Task Learning with Language Modeling for Question Generation (D19-1)
Copied to clipboard
| Challenge: | Existing work on answer-aware questions generates a sentence and answer span as input . previous work on QG was mainly tackled by rule-based approach and neural-based one . |
| Approach: | They propose to incorporate an auxiliary task of language modeling to help question generation in a hierarchical multi-task learning structure. |
| Outcome: | The proposed model improves on SQuAD and MARCO datasets and human evaluation proves it. |
FastFiD: Improve Inference Efficiency of Open Domain Question Answering via Sentence Selection (2024.acl-long)
Copied to clipboard
| Challenge: | Open Domain Question Answering (ODQA) is a longstanding task in Natural Language Processing that involves generating an answer solely based on a given question. |
| Approach: | They propose a novel approach that executes sentence selection on the encoded passages to enhance the inference speed while reducing the context length required for generating answers. |
| Outcome: | The proposed approach can increase inference speed by **2.3X-5.7X** while maintaining the model’s performance. |
Encoding Gated Translation Memory into Neural Machine Translation (D18-1)
Copied to clipboard
| Challenge: | Neural machine translation (MT) technology has made significant progress in the past few years. |
| Approach: | They propose a method to combine the strengths of TM and neural machine translation (NMT) they use a gating mechanism to balance the impact of the TM match on the NMT decoder . |
| Outcome: | The proposed method improves translation quality by over 10 BLEU points when fuzzy matches are higher than 50% on the UN corpus. |
Improving Cross-task Generalization of Unified Table-to-text Models with Compositional Task Configurations (2023.findings-acl)
Copied to clipboard
Jifan Chen, Yuhao Zhang, Lan Liu, Rui Dong, Xinchi Chen, Patrick Ng, William Yang Wang, Zhiheng Huang
| Challenge: | Existing methods for multitask learning typically use a dataset name as input prefix, which limits the effectiveness of multitask training. |
| Approach: | They propose compositional task configurations, a set of prompts prepended to the encoder to improve cross-task generalization of unified models. |
| Outcome: | The proposed model outperforms the UnifiedSKG baseline by noticeable margins in both in-domain and zero-shot settings. |
Curriculum Pre-training for End-to-End Speech Translation (2020.acl-main)
Copied to clipboard
| Challenge: | End-to-end speech translation requires a powerful encoder to transcribe, understand and learn cross-lingual semantics simultaneously. |
| Approach: | They propose a curriculum pre-training method that includes an elementary course for transcription learning and two advanced courses for understanding the utterance and mapping words in two languages. |
| Outcome: | The proposed method improves on En-De and En-Fr speech translation benchmarks. |
Semi-supervised Autoencoding Projective Dependency Parsing (2020.coling-main)
Copied to clipboard
| Challenge: | Existing models for semi-supervised dependency parsing use labeled data, but they require large amounts of labeles. |
| Approach: | They propose two end-to-end autoencoding models for semi-supervised graph-based projective dependency parsing. |
| Outcome: | The proposed models outperform a semi-supervised model on WSJ and UD dependency parsing data sets. |
SemFace: Pre-training Encoder and Decoder with a Semantic Interface for Neural Machine Translation (2021.acl-long)
Copied to clipboard
| Challenge: | Using pre-training methods for NMT models is difficult because of the cross-attention module . cross-linguistic embeddings are not used to pretrain a decoder . |
| Approach: | They propose a semantic interface between pre-trained encoder and pre-train decoder to improve NMT performance. |
| Outcome: | The proposed method improves on translation and unsupervised translation tasks. |
SimulSpeech: End-to-End Simultaneous Speech to Text Translation (2020.acl-main)
Copied to clipboard
| Challenge: | SimulSpeech is an end-to-end simultaneous speech to text translation system . conventional approaches to simultaneous speech translation divide the translation process into two stages . |
| Approach: | They develop an end-to-end simultaneous speech to text translation system which translates speech in source language to text in target language concurrently. |
| Outcome: | The proposed system achieves reasonable BLEU scores and lower delay compared to full-sentence translation model. |
RainProof: An Umbrella to Shield Text Generator from Out-Of-Distribution Data (2023.emnlp-main)
Copied to clipboard
| Challenge: | Out-of-distribution (OOD) detection is a widely covered topic in classification tasks, but most methods rely on hidden features output by the encoder. |
| Approach: | They propose to leverage soft-probabilities in a black-box framework to detect OOD . they propose to use a more operational evaluation setting to enable OOD detection . |
| Outcome: | The proposed framework can access soft-predictions but not the internal states of the model. |
ToXCL: A Unified Framework for Toxic Speech Detection and Explanation (2024.naacl-long)
Copied to clipboard
| Challenge: | Existing models that focus on explicit toxic speech detection and explanation are prone to error propagation problems . et al., 2018) show that toxic speech models can be prone for generating errors . |
| Approach: | They propose a framework that can detect and explain toxic speech using a target group generator and an encoder-decoder model. |
| Outcome: | The proposed model outperforms baseline models and achieves state-of-the-art effectiveness . the proposed model generates a toxic explanation that matches the ground truth explanation . |
An Exploration of Encoder-Decoder Approaches to Multi-Label Classification for Legal and Biomedical Text (2023.findings-acl)
Copied to clipboard
| Challenge: | Standard methods for multi-label text classification rely on encoder-only pre-trained models . encoder decoder models have proven more effective in other classification tasks . |
| Approach: | They compare four methods for multi-label classification based on encoder-only models . they use a pre-trained model for multilabel text classification . |
| Outcome: | The proposed methods outperform encoder-only methods on complex datasets and labeling schemes. |
Decoupled Vocabulary Learning Enables Zero-Shot Translation from Unseen Languages (2024.acl-long)
Copied to clipboard
| Challenge: | Multilingual neural machine translation systems learn to map sentences of different languages into a common representation space. |
| Approach: | They propose a setup where we decouple learning of vocabulary and syntax and train to translate while keeping those word representations frozen. |
| Outcome: | The proposed setup achieves near parity with a supervised setting on the TED domain with varying number of languages seen by the encoder. |
Entity Disambiguation via Fusion Entity Decoding (2024.naacl-long)
Copied to clipboard
Junxiong Wang, Ali Mousavi, Omar Attia, Ronak Pradeep, Saloni Potdar, Alexander Rush, Umar Farooq Minhas, Yunyao Li
| Challenge: | Existing generative approaches demonstrate improved accuracy compared to classification approaches under the standardized ZELDA benchmark. |
| Approach: | They propose an encoder-decoder model to disambiguate entities with more detailed entity descriptions. |
| Outcome: | The proposed model outperforms existing classification models on the ZELDA benchmark and on retrieval/reader frameworks. |
FastCorrect 2: Fast Error Correction on Multiple Candidates for Automatic Speech Recognition (2021.findings-emnlp)
Copied to clipboard
Yichong Leng, Xu Tan, Rui Wang, Linchen Zhu, Jin Xu, Wenjie Liu, Linquan Liu, Xiang-Yang Li, Tao Qin, Edward Lin, Tie-Yan Liu
| Challenge: | Error correction is widely used in automatic speech recognition (ASR) to post-process the generated sentence. |
| Approach: | They propose a fast correction model that takes multiple ASR candidates as input for better correction accuracy. |
| Outcome: | The proposed model can reduce the word error rate (WER) with multiple candidates by 3.2% and 2.6%. |
Character-level Representations Improve DRS-based Semantic Parsing Even in the Age of BERT (2020.emnlp-main)
Copied to clipboard
| Challenge: | a new method of analysis based on semantic tags demonstrates that character-level representations improve performance across a subset of selected semantic phenomena. |
| Approach: | They combine character-level and contextual language model representations to improve performance on Discourse Representation Structure parsing. |
| Outcome: | The proposed model improves performance on a subset of selected semantic phenomena. |
XAL: EXplainable Active Learning Makes Classifiers Better Low-resource Learners (2024.naacl-long)
Copied to clipboard
| Challenge: | Existing methods for active learning rely on model uncertainty or disagreement to pick unlabeled data, leading to over-confidence in superficial patterns and lack of exploration. |
| Approach: | They propose to use a bi-directional encoder and a uni-directional decoder to generate and score an explanation for low-resource text classification. |
| Outcome: | The proposed model improves on 9 strong baselines on six datasets and can generate explanations for its predictions. |
Event Representation with Sequential, Semi-Supervised Discrete Variables (2021.naacl-main)
Copied to clipboard
| Challenge: | Existing methods for event modeling take discrete, external knowledge into account . obtaining fully accurate structured knowledge can be difficult . |
| Approach: | They propose a method that takes partially-observed sequences of discrete, external knowledge into account. |
| Outcome: | The proposed method outperforms baselines and state-of-the-art in script induction and converges faster. |
Topic-Informed Dialogue Summarization using Topic Distribution and Prompt-based Modeling (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing models that deal with multiple topics are prone to topic drift . experimental results show that our model outperforms state-of-the-art methods on ROUGE scores . |
| Approach: | They propose a dialogue summarization model that reflects dialogue topic distribution to consider all topics present in a dialog. |
| Outcome: | The proposed model outperforms state-of-the-art methods on ROUGE scores and generates comprehensive summaries. |
Improving the Robustness of Summarization Systems with Dual Augmentation (2023.acl-long)
Copied to clipboard
| Challenge: | Experimental results show that state-of-the-art summarization models have a significant decrease in performance on adversarial and noisy test sets. |
| Approach: | They propose a SummAttacker approach to generate adversarial samples based on pre-trained language models that can generate word-level synonym substitution and noise. |
| Outcome: | The proposed model performs better on noisy, attacked, and clean datasets than baseline models and is more robust on noisy and attacked datasets. |
Efficiently Summarizing Text and Graph Encodings of Multi-Document Clusters (2021.naacl-main)
Copied to clipboard
| Challenge: | Abstractive multi-document summarization (MDS) is a task that has seen advances with the introduction of large-scale datasets and powerful Transformer-based models. |
| Approach: | They propose an efficient graph-enhanced approach to multi-document summarization with an encoder-decoder Transformer model. |
| Outcome: | The proposed model scales to large input documents and improves on a multi-document dataset. |
HyperNetwork-based Decoupling to Improve Model Generalization for Few-Shot Relation Extraction (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies cannot generalize well to unseen relations using Prototypical Networks . current approaches are dependent on large amount of labeled data and cannot deal with unseense relations well. |
| Approach: | They propose a HyperNetwork-based Decoupling approach to improve FSRE generalization . they propose FSre models with an encoder, network generator and refined classifiers . |
| Outcome: | The proposed method improves the generalization of few-shot relation extraction models. |
Effectiveness of Data Augmentation and Pretraining for Improving Neural Headline Generation in Low-Resource Settings (2022.lrec-1)
Copied to clipboard
| Challenge: | Neural approaches for natural language generation (NLG) have mushroomed due to large textual resources. |
| Approach: | They propose to use a pretrained multilingual encoder-decoder model and a combination of two pretrained language models to train a model in a low-resource setting. |
| Outcome: | The proposed model outperforms the previous model on English and on a small subset of the same data. |
Training Language Models with Memory Augmentation (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for training memory-augmented language models only introduce mem-ories at testing time or represent them using a separately trained encoder. |
| Approach: | They propose a training approach that directly takes in-batch examples as accessible memory and new methods for memory construction and data batching that are used for adapting to different sets of memories at testing time. |
| Outcome: | The proposed approach reduces perplexity from 18.70 to 15.37 on multiple language modeling and machine translation benchmarks. |
Knowledge-enhanced Multimodal ECG Representation Learning with Arbitrary-Lead Inputs (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Current methods for multimodal representation learning for electrocardiograms often result in suboptimal alignment of ECG signals with their corresponding text reports. |
| Approach: | They propose a framework to learn ECG representations by aligning ECG signals with paired free-text reports. |
| Outcome: | The proposed framework outperforms existing methods in zero-shot classification and linear probing tasks using 12 leads. |
Text Summarization with Pretrained Encoders (D19-1)
Copied to clipboard
| Challenge: | Existing pretraining languages such as ELMo and GPT have advanced a wide range of tasks. |
| Approach: | They propose a novel document-level encoder based on BERT which can express the semantics of a document and obtain representations for its sentences. |
| Outcome: | The proposed model achieves state-of-the-art in extractive and abstractive settings. |
Data-Informed Global Sparseness in Attention Mechanisms for Deep Neural Networks (2024.lrec-main)
Copied to clipboard
| Challenge: | Attention pruning techniques have been developed to identify and exploit sparseness . previous work has taken pioneering steps to discover and explain the sparsity in attention patterns . |
| Approach: | They propose a framework that observes attention patterns in a fixed dataset and generates a global sparseness mask. |
| Outcome: | The proposed approach saves 90% of computations and maintains quality of results. |
He is very intelligent, she is very beautiful? On Mitigating Social Biases in Language Modelling and Generation (2021.findings-acl)
Copied to clipboard
Aparna Garimella, Akhash Amarnath, Kiran Kumar, Akash Pramod Yalla, Anandhavelu N, Niyati Chhaya, Balaji Vasan Srinivasan
| Challenge: | Existing studies have focused on mitigating social biases in context-free representations, with recent shift to contextual ones. |
| Approach: | They propose an approach to mitigate social biases in a large pre-trained contextual language model . they propose lexical co-occurrence-based bias penalization in the decoder units . |
| Outcome: | The proposed approach reduces biases in fill-in-the-blank sentences and summarizes . it also reduces the biased representations in the frameworks, the authors show . |
Exploiting Invertible Decoders for Unsupervised Sentence Representation Learning (P19-1)
Copied to clipboard
| Challenge: | Encoder-decoder models for unsupervised sentence representation learning discard decoder after training . decoded sentences are often used to make better predictions of words in a given sentence . |
| Approach: | They propose two types of decoding functions whose inverse can be easily derived without expensive inverse calculation. |
| Outcome: | The proposed models can learn good representations from encoders and decoders without expensive calculations. |
NASH: A Simple Unified Framework of Structured Pruning for Accelerating Encoder-Decoder Language Models (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Structured pruning methods have proven effective in reducing the model size and accelerating inference speed in various network architectures. |
| Approach: | They propose a framework that narrows the encoder and shortens the decoder networks of encoder-decoder models. |
| Outcome: | The proposed framework reduces the number of decoder layers and improves generation quality. |
Keeping Notes: Conditional Natural Language Generation with a Scratchpad Encoder (P19-1)
Copied to clipboard
| Challenge: | Qualitative assessments in the form of human judgements (question generation), attention visualization (MT), and sample output (summarization) provide further evidence of the ability of Scratchpad to generate fluent and expressive output. |
| Approach: | They propose to use the encoder as a "scratchpad" memory to keep track of what has been generated and guide future generation. |
| Outcome: | The proposed mechanism improves the fluency of seq2seq models on three well-studied natural language generation tasks. |
SCRIPT: Self-Critic PreTraining of Transformers (2021.naacl-main)
Copied to clipboard
| Challenge: | Existing methods for representation learning of text are masked language modeling (MLM) a language model is trained to learn universal contextual embeddings, which are fine-tuned on a down-stream task. |
| Approach: | They propose a self-critic pretraining transformer for representation learning of text . they demonstrate improved sample-efficiency and improved performance over strong baselines . |
| Outcome: | The proposed model improves sample-efficiency and performance over strong baselines. |
Cross-Lingual Event Detection via Optimized Adversarial Training (2022.naacl-main)
Copied to clipboard
| Challenge: | Recent work in this area has harnessed the language-invariant qualities of pre-trained Multi-lingual Language Models. |
| Approach: | They propose to use adversarial language adaptation to train a model to detect events in a target language. |
| Outcome: | The proposed model achieves state-of-the-art on 8 different language pairs, using 4 languages from unrelated families. |
Stochastic Wasserstein Autoencoder for Probabilistic Sentence Generation (N19-1)
Copied to clipboard
| Challenge: | Experimental results show that the latent space learned by WAE exhibits properties of continuity and smoothness as in VAEs. |
| Approach: | They propose to use the variational autoencoder (VAE) for probabilistic sentence generation . they propose a variant of WAE that encourages the stochasticity of the encoder . |
| Outcome: | The proposed variant encourages the stochasticity of the encoder while achieving higher BLEU scores. |
On the Sub-layer Functionalities of Transformer Decoder (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Existing efforts to interpret the encoder of Transformer-based encoder-decoder architectures for neural machine translation have focused on assessing the encoded representations or interpreting the multi-head self-attentions. |
| Approach: | They propose to use Transformer-based encoder-decoder architectures to analyze how information is propagated through each module of each decoder layer. |
| Outcome: | The proposed model can be dropped with minimal loss of performance on three translation datasets and can be used to train and inference faster. |
End-to-End Synthetic Data Generation for Domain Adaptation of Question Answering Systems (2020.emnlp-main)
Copied to clipboard
Siamak Shakeri, Cicero Nogueira dos Santos, Henghui Zhu, Patrick Ng, Feng Nan, Zhiguo Wang, Ramesh Nallapati, Bing Xiang
| Challenge: | Existing approaches for synthetic QA data generation have limited or no success in improving the downstream Reading Comprehension task. |
| Approach: | They propose an end-to-end approach for synthetic QA data generation using a transformer-based encoder-decoder network that is trained end- to-end to generate both answers and questions. |
| Outcome: | The proposed model outperforms current state-of-the-art methods in the domain adaptation of QA models. |
Closed-Book Training to Improve Summarization Encoder Memory (D18-1)
Copied to clipboard
| Challenge: | Extractive summarization models pick words, phrases, and sentences from the source text to form a summary, while abstractive models generate (samples) words from a fixed-size vocabulary instead of copying from text directly. |
| Approach: | They propose to add an additional ‘closed-book’ decoder without attention and pointer mechanisms to the model to improve its memorization capabilities. |
| Outcome: | The proposed model outperforms the baseline model on the CNN/Daily Mail dataset in terms of ROUGE and METEOR metrics, and achieves higher scores in a test-only setup. |
DiffusionDialog: A Diffusion Model for Diverse Dialog Generation with Latent Space (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing studies have tried to introduce discrete or Gaussian-based latent variables to address the one-to-many problem, but the diversity is limited. |
| Approach: | They propose a diffusion model to enhance the diversity of dialogue generation by using continuous latent variables instead of discrete ones. |
| Outcome: | The proposed model greatly enhances diversity of dialog response while keeping the coherence. |
Highlight-Transformer: Leveraging Key Phrase Aware Attention to Improve Abstractive Multi-Document Summarization (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing models do not consider key phrases in determining attention weights of self-attention . Existing work does not consider the importance of key phrases when determining weights . |
| Approach: | They propose a model with highlighting mechanism to assign greater attention weights to key phrases . they propose two structures of highlighting attention for each head and the multihead highlighting . experimental results show that their proposed model significantly outperforms the baseline model . |
| Outcome: | The proposed model outperforms the baseline models on a multi-news dataset. |
Disentangling Pretrained Representation to Leverage Low-Resource Languages in Multilingual Machine Translation (2024.lrec-main)
Copied to clipboard
| Challenge: | Multilingual neural machine translation requires an enormous dataset, leaving the low-resource language (LRL) underdeveloped. |
| Approach: | They evaluated five languages using a parallel corpus of 1,000 instances each and found a zero-shot improvement of 7.4 from the baseline score of 7.1 to a score of 15.5 at best. |
| Outcome: | The proposed model improves performance in the linguistically diverse country of Indonesia by 7.4 from baseline score of 7.1 to 15.5 at best. |
OssCSE: Overcoming Surface Structure Bias in Contrastive Learning for Unsupervised Sentence Embedding (2023.emnlp-main)
Copied to clipboard
Zhan Shi, Guoyin Wang, Ke Bai, Jiwei Li, Xiang Li, Qingjun Cui, Belinda Zeng, Trishul Chilimbi, Xiaodan Zhu
| Challenge: | Recent studies show that contrastive learning is effective in sentence representation learning . but, the surface structure bias is a problem in the current model . |
| Approach: | They propose to combine a sentence with a sub-semantic sentence to investigate the surface structure bias. |
| Outcome: | The proposed model achieves state-of-the-art on standard semantic textual similarity tasks using different pre-trained backbones. |
Mitigating Shortcut Learning with InterpoLated Learning (2025.acl-long)
Copied to clipboard
| Challenge: | Existing shortcut mitigation approaches are model-specific, difficult to tune, computationally expensive, and fail to improve learned representations. |
| Approach: | They propose to interpolate representations of majority examples to include features from intra-class minority examples with shortcut-mitigating patterns. |
| Outcome: | The proposed method improves minority generalization over ERM and state-of-the-art mitigation methods on multiple natural language understanding tasks while preserving accuracy on majority examples. |
A Representation Level Analysis of NMT Model Robustness to Grammatical Errors (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing work on robustness failures or improving robustness has focused on documenting failures . however, there has been limited analysis of model representations in response to noise. |
| Approach: | They perform Grammatical Error Detection probing and representational similarity analysis to examine model representations of ungrammatical inputs and how they evolve through model layers. |
| Outcome: | The proposed model detects and corrects the grammatical error by moving its representation toward the correct form. |
LLM Distillation for Efficient Few-Shot Multiple Choice Question Answering (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Large Language Models excel at few-shot learning but their direct application in real-world scenarios is often hindered by their high computational cost. |
| Approach: | They propose a framework that uses Large Language Models for data generation and scoring to improve encoder model performance. |
| Outcome: | The proposed approach improves accuracy from 28.9% to 39.3% on a few-shot MCQA task . |
Improving Event Coreference Resolution Using Document-level and Topic-level Information (2022.emnlp-main)
Copied to clipboard
| Challenge: | Experimental results show that our model outperforms the SOTA baselines due to the encoding length limitation. |
| Approach: | They propose a longformer-based encoder and an encoder with a trigger-mask mechanism to learn sentence-level embeddings based on local context. |
| Outcome: | The proposed model outperforms the baselines on the KBP 2017 dataset. |
DiffuseDef: Improved Robustness to Adversarial Attacks via Iterative Denoising (2025.acl-long)
Copied to clipboard
| Challenge: | Existing adversarial defense methods for natural language processing still pose challenges to adversarials. |
| Approach: | They propose a novel adversarial defense method that incorporates a diffusion layer as a denoiser between the encoder and the classifier. |
| Outcome: | The proposed method improves over existing adversarial defense methods and achieves state-of-the-art performance against black-box and white-box adversarials. |
NeuroMax: Enhancing Neural Topic Modeling via Maximizing Mutual Information and Group Topic Regularization (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Recent advances in neural topic models have focused on two main directions: the integration of the inference network with a pre-trained language model and the modeling of the relationship between words and topics in the generative model. |
| Approach: | They propose a framework to maximize mutual information between topics and PLMs . Experimental results indicate that NeuroMax reduces inference time . |
| Outcome: | The proposed framework reduces inference time, generates more coherent topics and topic groups, and produces more representative document embeddings. |
Improving Encoder by Auxiliary Supervision Tasks for Table-to-Text Generation (2021.acl-long)
Copied to clipboard
| Challenge: | Experimental results show that our method not only has a good generalization but also outperforms previous methods on several metrics: BLEU, Content Selection, Content Ordering. |
| Approach: | They propose to build an entity graph from the input tables and introduce a reasoning module to perform reasoning on the graph. |
| Outcome: | The proposed method outperforms previous methods on several metrics: BLEU, Content Selection, Content Ordering. |
On Robustness of Finetuned Transformer-based NLP Models (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Pretrained Transformer-based language models have been finetuned for a large number of tasks. |
| Approach: | They characterize changes between pretrained and finetuned models with CKA and STIR metrics. |
| Outcome: | The proposed models are more robust to perturbations than BERT and T5 on classification tasks and generation tasks. |
Probabilistic Transformer: A Probabilistic Dependency Model for Contextual Word Representation (2023.findings-acl)
Copied to clipboard
| Challenge: | Syntactic structures were deemed essential in natural language processing . but since the deep learning revolution, NLP has been dominated by neural models that do not consider syntactical structures in their design. |
| Approach: | They propose a model that models latent representations of words in a sentence . they use a conditional random field to model latent and dependency arcs . |
| Outcome: | The proposed model performs competitively to transformers on small to medium sized datasets. |
Improving Zero-Shot Multilingual Translation with Universal Representations and Cross-Mapping (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing model structure and training scheme cannot ensure universal representations and cross-mappings because of lacking explicit constraints. |
| Approach: | They propose a state mover’s distance model to model the difference of the representations output by the encoder and a agreement-based training scheme to minimize the proposed distance to learn universal representations. |
| Outcome: | The proposed model can translate between languages unseen during training, i.e., zero-shot translation. |
Faster Speculative Decoding via Effective Draft Decoder with Pruned Candidate Tree (2025.acl-long)
Copied to clipboard
| Challenge: | Effective Draft Decoder (EDD) is a powerful decoding method that generates more accurate draft tokens by leveraging the encoding results as soft prompts. |
| Approach: | They propose an effective draft decoder which treats the LLM as a powerful encoder and generates more accurate draft tokens by leveraging the encoding results as soft prompts. |
| Outcome: | The proposed method significantly improves the performance of large language models and reduces inference latency. |
EDDA: An Encoder-Decoder Data Augmentation Framework for Zero-Shot Stance Detection (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing methods for enhancing text or data are limited by lack of logical connections between generated texts and training data. |
| Approach: | They propose an encoder-decoder data augmentation framework that combines large language models and chain-of-thought prompting to summarize texts into target-specific if-then rationales, establishing logical relationships. |
| Outcome: | The proposed framework significantly improves over state-of-the-art methods on benchmark datasets while enabling interpretable rationale-based learning. |
Multimodal Sentence Summarization via Multimodal Selective Encoding (2020.coling-main)
Copied to clipboard
| Challenge: | Existing methods for generating summary from text and image ignore that the image can improve the ability of the encoder to identify highlights of a news event or document. |
| Approach: | They propose a multimodal selective gate network that takes reciprocal relationships between textual and multi-level visual features into account to select highlights of the event. |
| Outcome: | The proposed model can generate summary for a given sentence-image pair using visual signals . it can also capture highlights embedded in the image more accurately, the authors show . |
Coherent Entity Disambiguation via Modeling Topic and Categorical Dependency (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing entity disambiguation methods struggle to capture explicit discourse-level dependencies, resulting in incoherent predictions at the abstract level. |
| Approach: | They propose an unsupervised variational autoencoder to extract latent topic vectors of context sentences to enhance coherence of entity predictions. |
| Outcome: | The proposed system achieves state-of-the-art on popular ED benchmarks with an average improvement of 1.3 F1 points. |
Pretraining with Artificial Language: Studying Transferable Knowledge in Language Models (2022.acl-long)
Copied to clipboard
| Challenge: | Existing studies show that pretraining with an artificial language with nesting dependency structure provides some knowledge transferable to natural language. |
| Approach: | They propose to pretrain artificial languages with structural properties that mimic natural language and then test their performance on downstream tasks. |
| Outcome: | The proposed language models show strong performance across languages and languages. |
A Novel Estimator of Mutual Information for Learning to Disentangle Textual Representations (2021.acl-long)
Copied to clipboard
| Challenge: | Existing methods for learning disentangled representations of textual data are difficult to implement and suffer from the degeneracy of other losses in multi-class scenarios. |
| Approach: | They propose a variational upper bound to the mutual information between an attribute and the latent code of an encoder that controls the approximation error. |
| Outcome: | The proposed method is superior on fair classification and on textual style transfer tasks. |
Multi-Figurative Language Generation (2022.coling-1)
Copied to clipboard
| Challenge: | Figurative language generation is the task of reformulating a given text in the desired figure of speech while still being faithful to the original context. |
| Approach: | They propose a scheme for multi-figurative language pre-training on top of BART and a mechanism for injecting the target figurative information into the encoder to generate text with the target figure from another figurativ form without parallel figura-figura pairs. |
| Outcome: | The proposed model outperforms all baselines and qualitatively examines the relationship between the different figures of speech. |
Diffusion Lens: Interpreting Text Encoders in Text-to-Image Pipelines (2024.acl-long)
Copied to clipboard
| Challenge: | Text-to-image diffusion models use a latent text prompt to guide image generation . however, the process by which the encoder produces the text representation is unknown . |
| Approach: | They propose a method for analyzing the text encoder of T2I models by generating images from its intermediate representations. |
| Outcome: | The proposed method provides valuable insights into the text encoder component in T2I pipelines. |
The Transference Architecture for Automatic Post-Editing (2020.coling-main)
Copied to clipboard
| Challenge: | A research challenge is the search for architectures that best support the capture, preparation and provision of src and mt information and its integration with pe decisions. |
| Approach: | They propose a multi-encoder based neural APE model that conditions post-editing decisions on both the source and machine translated text as inputs. |
| Outcome: | The proposed model outperforms the best performing systems by 1 BLEU point on the WMT 2016, 2017, and 2018 English–German APE shared tasks. |
Time-aware Prompting for Text Generation (2022.findings-emnlp)
Copied to clipboard
| Challenge: | a new study investigates the effects of incorporating timestamps into generation systems . textual prompts focus more on non-temporal information and are less sensitive to given timestams . |
| Approach: | They propose a data-to-text generation dataset that includes chronologically ordered revisions of biographical articles from English Wikipedia. |
| Outcome: | The proposed models improve the quality of the data-to-text generation dataset TempWikiBio . the proposed models are more sensitive to time-aware prompts than textual prompts . |
Guiding Neural Machine Translation with Semantic Kernels (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Empirical studies show that our approach gains approximately an improvement of 1 BLEU score on most benchmarks over the Transformer baseline. |
| Approach: | They propose to extract several semantic kernels from a source sentence to capture global semantic information. |
| Outcome: | Empirical results show that the proposed approach improves 1 BLEU score on benchmarks . it is also 1.7 times faster than previous works on average at inference time . |
HiSMatch: Historical Structure Matching based Temporal Knowledge Graph Reasoning (2022.findings-emnlp)
Copied to clipboard
Zixuan Li, Zhongni Hou, Saiping Guan, Xiaolong Jin, Weihua Peng, Long Bai, Yajuan Lyu, Wei Li, Jiafeng Guo, Xueqi Cheng
| Challenge: | Temporal Knowledge Graphs (TKGs) store facts as triples in the form of subject, relation, object, timestamps. |
| Approach: | They propose a Temporal Knowledge Graph (TKG) model that extends each triple with a timestamp to describe dynamic facts. |
| Outcome: | The proposed model improves on six benchmark datasets with up to 5.6% performance improvement compared to the state-of-the-art models. |
PromptRank: Unsupervised Keyphrase Extraction Using Prompt (2023.acl-long)
Copied to clipboard
| Challenge: | Existing keyphrase extraction methods struggle with document and candidate length discrepancies or fail to fully utilize the pre-trained language model without further fine-tuning. |
| Approach: | They propose an unsupervised keyphrase extraction approach that uses a pre-trained language model to rank candidates based on document embeddings. |
| Outcome: | The proposed approach outperforms the existing keyphrase extraction approach on six benchmarks. |
LCS: A Language Converter Strategy for Zero-Shot Neural Machine Translation (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing LT strategies cannot indicate the desired target language on zero-shot translation, i.e., the off-target issue. |
| Approach: | They propose a language converter strategy that embeds the target language into the top encoder layers to mitigate confusion in the encoder and ensures stable language indication for the decoder. |
| Outcome: | The proposed language converter strategy significantly mitigates off-target issue on multiUN, TED, and OPUS-100 datasets. |
PSP: Pre-trained Soft Prompts for Few-Shot Abstractive Summarization (2022.coling-1)
Copied to clipboard
| Challenge: | Experimental results show that our method outperforms full-model tuning in few-shot abstractive summarization tasks. |
| Approach: | They propose a soft prompts architecture with prompt pre-training and prompt fine-tuning paradigm to support few-shot abstractive summarization. |
| Outcome: | The proposed model outperforms Prompt Tuning and Profix-Tuning on CNN/DailyMail and XSum datasets and outperfies Profix Tuning by a large margin. |
Hierarchical Bi-Directional Self-Attention Networks for Paper Review Rating Recommendation (2020.coling-main)
Copied to clipboard
| Challenge: | Existing methods for review rating prediction ignore hierarchies among data . paper review rating predictions are important for improving paper review process . |
| Approach: | They propose a Hierarchical bi-directional self-attention Network framework for paper review rating prediction and recommendation . they leverage hierarchical structure of paper reviews with three levels of encoders . |
| Outcome: | The proposed approach can be used to make an effective decision-making tool for the academic paper review process. |
Just Like a Human Would, Direct Access to Sarcasm Augmented with Potential Result and Reaction (2023.acl-long)
Copied to clipboard
| Challenge: | sarcasm is a form of irony conveying mockery and contempt . social media has become increasingly popular for identifying sarcasm . |
| Approach: | They develop a method to detect sarcasm from social media using augmented potentials. |
| Outcome: | The proposed method outperforms baselines on benchmark datasets. |
Quick Back-Translation for Unsupervised Machine Translation (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Unsupervised machine translation models are limited by the run-time of autoregressive inference during back-translation and lack of synthetic data efficiency. |
| Approach: | They propose a two-for-one improvement to Transformer back-translation: Quick Back-Translation (QBT). QBT re-purposes the encoder as a generative model, and uses encoder-generated sequences to train the decoder. |
| Outcome: | Experiments on various WMT benchmarks show that QBT dramatically outperforms standard back-translation only method in terms of training efficiency for comparable translation qualities. |
Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned (P19-1)
Copied to clipboard
| Challenge: | et al., 2017) show that multi-head attention is important for neural machine translation. |
| Approach: | They evaluate the contribution made by individual attention heads to the overall performance of the Transformer model and analyze the roles played by them in the encoder. |
| Outcome: | The proposed pruning method removes the vast majority of heads without affecting performance. |
Few-Shot Learning with Siamese Networks and Label Tuning (2022.acl-long)
Copied to clipboard
| Challenge: | Recent studies have shown that few-shot text classification is a poor solution for training data-intensive tasks. |
| Approach: | They propose a method that embeds texts and labels into classifiers with proper pre-training. |
| Outcome: | The proposed approach reduces inference cost by increasing the number of labels and embeddings. |
Incremental Transformer: Efficient Encoder for Incremented Text Over MRC and Conversation Tasks (2025.coling-main)
Copied to clipboard
| Challenge: | Existing encoders that encode incremented inputs have to re-encode the whole text to obtain the encoding of the extended input. |
| Approach: | They propose an efficient encoder dedicated for faster encoding of incremented input . it takes only added input as input but attends to cached representations of original input a lower layer . |
| Outcome: | The proposed encoder achieves 6.2x speedup over current encoders . it takes only added input as input but attends to cached representations of original input . |
Recipes for Sequential Pre-training of Multilingual Encoder and Seq2Seq Models (2023.findings-acl)
Copied to clipboard
| Challenge: | Pre-trained encoder-only and sequence-to-sequence models are computationally expensive. |
| Approach: | They propose a recipe to initialize one model from the other to improve pre-training efficiency. |
| Outcome: | The proposed method matches the performance of a from-scratch model with a multilingual encoder while reducing the total compute cost by 27%. |
Single-to-mix Modality Alignment with Multimodal Large Language Model for Document Image Machine Translation (2025.acl-long)
Copied to clipboard
| Challenge: | Document Image Machine Translation (DIMT) faces generalization challenges due to limited training data and the complex interplay between visual and textual information. |
| Approach: | They propose a single-to-mix Modality alignment framework leveraging Multimodal Large Language Models (MLLMs) this framework aligns an imageonly encoder with multimodal representations of an MLLM pre-trained on large-scale document image datasets. |
| Outcome: | The proposed framework improves translation quality in cross-domain generalization and challenging document image scenarios. |
Semi-Supervised Semantic Dependency Parsing Using CRF Autoencoders (2020.acl-main)
Copied to clipboard
| Challenge: | Semantic dependency parsing allows words to have multiple dependency heads, resulting in graph-structured representations. |
| Approach: | They propose an approach to semi-supervised learning of semantic dependency parsers based on the CRF autoencoder framework. |
| Outcome: | The proposed model improves over the baseline model and is arc-factored. |
Weakly-Supervised Spoken Video Grounding via Semantic Interaction Learning (2023.acl-long)
Copied to clipboard
| Challenge: | Recent work on spoken video grounding challenges extracting semantic information from speech . previous studies focused on textual queries, but recent work focuses on spoken queries . |
| Approach: | They propose a framework for weakly-supervised spoken video grounding to represent cross-modal semantics without expensive temporal annotations. |
| Outcome: | The proposed framework is more efficient than existing methods. |
Neural Topic Modeling based on Cycle Adversarial Training and Contrastive Learning (2023.findings-acl)
Copied to clipboard
| Challenge: | Neural topic models have been widely used to extract common topics across documents. |
| Approach: | They propose a framework to apply contrastive learning directly to the decoder . they propose 'self-supervised' contrastive loss to make the generator capture similar topic information . |
| Outcome: | The proposed framework outperforms baselines on four benchmark datasets. |
Exploiting Sentential Context for Neural Machine Translation (P19-1)
Copied to clipboard
| Challenge: | Existing approaches to exploit sentential context for machine translation are not well studied. |
| Approach: | They propose a shallow sentential context that exploits top encoder layer, and a deep sentential one that aggregates sentential representations from all internal layers. |
| Outcome: | The proposed model outperforms the strong Transformer model on the English-German and English-French benchmarks. |
Recycle Your Wav2Vec2 Codebook: A Speech Perceiver for Keyword Spotting (2022.coling-1)
Copied to clipboard
| Challenge: | Pretraining a keyword Spotting model with a pretraining encoder is expensive and requires a quadratic cost. |
| Approach: | They propose to recycle phonetic information encoded in wav2vec2.0's latent codebook, which has been typically thrown away after pretraining. |
| Outcome: | The proposed model can be initialized with phonetic embeddings, and it delivers accuracy gains at no latency costs. |
Unveiling the Role of Pretraining in Direct Speech Translation (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to train direct speech-to-text translation systems are pretraining the encoder on automatic speech recognition, thus losing efficiency in the training process. |
| Approach: | They propose to change the decoder cross-attention to integrate source information from earlier steps in training. |
| Outcome: | The proposed model can achieve comparable performance to the pretrained model while reducing training time. |
Cross-Domain Fake News Detection based on Dual-Granularity Adversarial Training (2025.coling-main)
Copied to clipboard
| Challenge: | Existing approaches to detect fake news in unseen domains are limited by domain-specific training. |
| Approach: | They propose a cross-domain fake news detection method based on adversarial training . they use a document-level and entity-level model to generate domain-independent representations . |
| Outcome: | The proposed method can detect fake news in unseen domains with the help of pre-trained language models. |
Analogical Math Word Problems Solving with Enhanced Problem-Solution Association (2022.emnlp-main)
Copied to clipboard
| Challenge: | Analogical reasoning has long been used in mathematical education, as it enables students to apply common relational structures of mathematical situations to solve new problems. |
| Approach: | They propose to leverage analogical MWPs to advance the solver’s generalization ability across different kinds of MWps. |
| Outcome: | The proposed model has a stronger generalization ability in solving difficult MWPs due to the analogical learning from easy MWPS. |
ConFit v2: Improving Resume-Job Matching using Hypothetical Resume Embedding and Runner-Up Hard-Negative Mining (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to model resume-job fit are sparse since job seekers apply to only a few jobs. |
| Approach: | They propose two techniques to enhance the encoder’s contrastive training process by augmenting job data with hypothetical reference resume generated by a large language model and creating high-quality hard negatives from unlabeled resume/job pairs using a novel hard-negative mining strategy. |
| Outcome: | The proposed method outperforms ConFit and prior methods on two real-world datasets and achieves an average improvement of 13.8% in recall and 17.5% in nDCG across job-ranking and resume-ranker tasks. |
Rethinking Data Augmentation for Low-Resource Neural Machine Translation: A Multi-Task Learning Approach (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to generating additional parallel sentences are aimed at expanding the support of the empirical data distribution by generating new sentence pairs that contain infrequent words. |
| Approach: | They propose to use data augmentation techniques to generate additional parallel sentences by reversing the order of the target sentence to produce unfluent target sentences. |
| Outcome: | The proposed approach improves on six low-resource translation tasks and the baseline and over DA methods. |
Neural Topic Modeling via Contextual and Graph Information Fusion (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing topic models generate uninformative and incoherent topics that hinder interpretable insights from managing textual data. |
| Approach: | They propose to incorporate contextual and graph information to improve the variational autoencoder framework by combining contextual and bag-of-words information. |
| Outcome: | The proposed framework generates more coherent and diverse topics on three benchmark datasets and achieves strong performance on automatic and manual evaluations. |
Parallel Refinements for Lexically Constrained Text Generation with BART (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing work injects lexical constraints into the output, which generates generic or ungrammatical sentences and has high computational complexity. |
| Approach: | They propose a model that incorporates pre-specified keywords into the output to control the generated text. |
| Outcome: | The proposed model decomposes the generated text into two sub-tasks and improves the sentence quality. |
Revealing the Myth of Higher-Order Inference in Coreference Resolution (2020.emnlp-main)
Copied to clipboard
| Challenge: | Adapted coreference resolution models have only marginally improved performance over representation learning. |
| Approach: | They implement an end-to-end coreference system and four HOI approaches to analyze the impact of higher-order inference on coreference resolution. |
| Outcome: | The proposed model shows that the impact of higher-order inference (HOI) on coreference resolution is negative to marginal, providing a new perspective on the task. |
Hard-Coded Gaussian Attention for Neural Machine Translation (2020.acl-main)
Copied to clipboard
| Challenge: | Recent work has questioned the importance of multi-headed attention in achieving high translation quality. |
| Approach: | They develop a “hard-coded” attention variant without any learned parameters. |
| Outcome: | The proposed model reduces BLEU scores by adding a single learned cross attention head to an otherwise hard-coded Transformer. |
On the Dimensionality of Sentence Embeddings (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing work focuses on improving the quality of sentence embeddings, but the exploration of sentence dimension is limited. |
| Approach: | They propose a two-step training method where the encoder and pooler are optimized separately to mitigate the overall performance loss in low-dimension scenarios. |
| Outcome: | The proposed method significantly improves the performance of low-dimensional sentence embeddings on seven STS tasks and seven sentence classification tasks. |
From Sights to Insights: Towards Summarization of Multimodal Clinical Documents (2024.acl-long)
Copied to clipboard
| Challenge: | a recent WHO report highlights a drastic doctor-to-patient ratio . telehealth is one of the most impactful sectors where AI advances can bring a significant revolution . |
| Approach: | They propose an image-guided encoder-decoder model that uses contextual attention to create detailed visual-guides for multimodal documents. |
| Outcome: | The proposed model outperforms state-of-the-art models on multimodal question and dialogue summarization tasks. |
Neural Topic Modeling with Cycle-Consistent Adversarial Training (2020.emnlp-main)
Copied to clipboard
| Challenge: | Recent advances on deep generative models have attracted significant interest in neural topic modeling. |
| Approach: | They propose an adversarial-neural topic model which uses Dirichlet prior to capture the semantic patterns in latent topics. |
| Outcome: | The proposed models outperform competing models on unsupervised/supervised topic modeling and text classification. |
A State-independent and Time-evolving Network for Early Rumor Detection in Social Media (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods to rumor detection ignored dynamical evolution of an event and failed to capture its unique features in different states. |
| Approach: | They propose a state-independent and time-evolving Network (STN) for rumor detection based on fine-grained event state detection and segmentation. |
| Outcome: | The proposed framework can significantly improve the rumor detection accuracy in comparison with some strong baseline systems. |
Chunk, Align, Select: A Simple Long-sequence Processing Method for Transformers (2024.acl-long)
Copied to clipboard
| Challenge: | Existing transformer-based models struggle with long-sequence processing due to computational costs . a framework to enhance long-content processing of transformers is proposed . |
| Approach: | They propose a framework to enhance long-sequence processing of transformers by three steps . they demonstrate that the framework significantly outperforms prior long-quence processors . |
| Outcome: | The proposed framework outperforms baseline models on long-sequence summarization and reading comprehension tasks. |
FiDO: Fusion-in-Decoder optimized for stronger performance and faster inference (2023.findings-acl)
Copied to clipboard
Michiel de Jong, Yury Zemlyanskiy, Joshua Ainslie, Nicholas FitzGerald, Sumit Sanghai, Fei Sha, William Cohen
| Challenge: | Fusion-in-Decoder (FiD) is a powerful retrieval-augmented language model . however, the architecture used for FiD was not designed for retrieval augmented models . |
| Approach: | They propose to make FiD a modified retrieval-augmented language model with a large decoder and memory bandwidth constraints to alleviate memory bandwidth limitations. |
| Outcome: | The proposed architecture outperforms existing models on knowledge-intensive tasks even on large models on many knowledge-based tasks. |
Sparsity and Sentence Structure in Encoder-Decoder Attention of Summarization Systems (2021.emnlp-main)
Copied to clipboard
| Challenge: | Training and inference using large transformer models can be computationally expensive because the self-attention's time and memory grow quadratically with sequence length. |
| Approach: | They propose a modified transformer architecture that constrains the encoder-decoder attention mechanism to a subset of input sentences while maintaining system performance. |
| Outcome: | The proposed architecture can be trained and inferenced using large transformer models with expensive training and induction costs. |
SamToNe: Improving Contrastive Loss for Dual Encoder Retrieval Models with Same Tower Negatives (2023.findings-acl)
Copied to clipboard
| Challenge: | Dual encoders have been used for retrieval tasks and representation learning with good results. |
| Approach: | They propose an improved contrastive learning objective by adding queries or documents from the same encoder towers to the negatives. |
| Outcome: | The proposed model improves retrieval quality for both symmetric and asymmetric dual encoders by adding queries or documents from the same encoder towers to the negatives. |
Revisiting Non-Autoregressive Translation at Scale (2023.findings-acl)
Copied to clipboard
| Challenge: | Extensive experiments on two advanced NAT models show scaling can improve translation performance. |
| Approach: | They empirically examine the impact of scaling on NAT behaviors on a large-scale WMT dataset. |
| Outcome: | The proposed model can achieve comparable performance with the scaling model while maintaining the superiority of decoding speed with standard NAT models. |
Inflate and Shrink:Enriching and Reducing Interactions for Fast Text-Image Retrieval (2021.emnlp-main)
Copied to clipboard
| Challenge: | a recent study shows that late-interaction methods trade off retrieval accuracy and efficiency by exploiting cross-modal interactions only in the late stage. |
| Approach: | They propose an inflating and shrinking approach to exploit cross-modal interactions . they inflate code inputs and shrink code outputs to exploit interactions progressively . |
| Outcome: | The proposed method exploits cross-modal interactions in the late stage to achieve retrieval speed. |
Revisiting Higher-Order Dependency Parsers (2020.acl-main)
Copied to clipboard
| Challenge: | Neural encoders have allowed dependency parsers to shift from higher-order structured models to simpler first-order ones, making decoding faster and still achieving better accuracy than non-neural parser. |
| Approach: | They found that neural parsers may benefit from higher-order features when employing a powerful pre-trained encoder, such as BERT. |
| Outcome: | Using a pre-trained encoder, we found that higher-order models are more accurate on full sentence parses and match of modifier lists. |
Abstractive Text Summarization based on Language Model Conditioning and Locality Modeling (2020.lrec-1)
Copied to clipboard
Dmitrii Aksenov, Julian Moreno-Schneider, Peter Bourgonje, Robert Schwarzenberg, Leonhard Hennig, Georg Rehm
| Challenge: | Abstractive summarization is an NLP task with many real-world applications. |
| Approach: | They propose to use a pre-trained language model to train a Transformer-based neural model . they propose a new method of BERT-windowing to allow chunk-wise processing of texts longer than the BERT window size . |
| Outcome: | The proposed model outperforms baseline models on CNN/Daily Mail dataset and shows its superiority on German dataset. |
MoCoKGC: Momentum Contrast Entity Encoding for Knowledge Graph Completion (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to knowledge graph completion have not integrated the structural attributes of knowledge graphs with the textual descriptions of entities to generate robust entity encodings. |
| Approach: | They propose to integrate structural information from knowledge graphs with textual descriptions of entities to generate robust entity encodings. |
| Outcome: | The proposed model improves on the standard evaluation metric, Mean Reciprocal Rank (MRR), while surpassing the current best model on the Wikidata5M dataset. |
Multilingual Encoder Knows more than You Realize: Shared Weights Pretraining for Extremely Low-Resource Languages (2025.acl-long)
Copied to clipboard
| Challenge: | XLM-R and mBART have advanced multilingualism in NLP, but low-resource languages such as Tibetan, Uyghur, Kazakh, and Mongolian are underserved. |
| Approach: | They propose a framework for adapting multilingual encoders to text generation in extremely low-resource languages by reusing the weights between the encoder and the decoder. |
| Outcome: | The proposed framework performs better on various downstream tasks even when compared with much larger models. |
LightVLP: A Lightweight Vision-Language Pre-training via Gated Interactive Masked AutoEncoders (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing vision-language pre-training models use multi-modal encoders to encode image and text, causing noisy training corpora. |
| Approach: | They propose a vision-language pre-training framework with two autoencoders for efficient training . they propose masked tokens and a gated interaction mechanism to cope with noise . |
| Outcome: | The proposed model achieves 2.2% R@1 gains on COCO Text Retrieval and 1.1% on refCOCO+ on six datasets. |
Deciphering the Interplay of Parametric and Non-parametric Memory in Retrieval-augmented Language Models (2024.emnlp-main)
Copied to clipboard
| Challenge: | Generative language models struggle with specialized knowledge that is discussed less frequently on the web. |
| Approach: | They propose to use a model which decides between parametric and non-parametric knowledge to investigate how it uses the information from the context. |
| Outcome: | The proposed model can choose between parametric and non-parametric information, but relies more on context than parametric knowledge. |
Cramming 1568 Tokens into a Single Vector and Back Again: Exploring the Limits of Embedding Space Capacity (2025.acl-long)
Copied to clipboard
| Challenge: | Recent work addresses problem of compression of tokens into shorter sequence of real-valued vectors . attainable lossless compression ratio is typically not higher than x10 . |
| Approach: | They propose to compress a sequence of tokens into a shorter sequence of real-valued vectors to be used as inputs instead of token embeddings or key-value cache. |
| Outcome: | The proposed algorithms reduce the amount of compute in existing language models rather than minimizing number of bits needed to store text. |
PFA-ERC: Psuedo-Future Augmented Dynamic Emotion Recognition in Conversations (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Current technologies in ERC are limited due to the need for future information. |
| Approach: | They propose a time-series forecasting transformer that predicts pseudo-future information to overcome this constraint. |
| Outcome: | The proposed method achieves state of the art performance on three ERC datasets - MELD, EmoryNLP, and IEMOCap. |
Flipping Knowledge Distillation: Leveraging Small Models’ Expertise to Enhance LLMs in Text Matching (2025.acl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have demonstrated remarkable capabilities in acquiring diverse knowledge, making them highly effective across a wide range of tasks. |
| Approach: | They propose a flipped knowledge distillation paradigm where LLM learns from SLM . they propose to reinterpret LLMs as encoder-decoder models using LoRA . |
| Outcome: | The proposed model has been deployed in an online application environment and validated on financial and healthcare benchmarks and real-world applications. |
TransAlign: Machine Translation Encoders are Strong Word Aligners, Too (2025.findings-emnlp)
Copied to clipboard
| Challenge: | translation-based approaches to cross-lingual transfer (XLT) are limited. |
| Approach: | They propose a word aligner that utilizes the encoder of a massively multilingual MT model. |
| Outcome: | The proposed word aligner outperforms existing WA and state-of-the-art non-WA-based methods in token classification tasks. |
Exploring the Hidden Capacity of LLMs for One-Step Text Generation (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large language models (LLMs) can reconstruct surprisingly long texts via autoregressive generation from just one trained input embedding. |
| Approach: | They show that large language models can reconstruct surprisingly long texts via autoregressive generation from just one trained input embedding. |
| Outcome: | The proposed model can generate hundreds of accurate tokens in one token-parallel forward pass, when provided with only two learned embeddings. |
Transition-Matrix Regularization for Next Dialogue Act Prediction in Counselling Conversations (2026.findings-acl)
Copied to clipboard
| Challenge: | Evaluated on a 60-class German counselling taxonomy, this improves macro-F1 by 9–42% relative depending on encoder and corpus-derived transition patterns. |
| Approach: | They propose to use a KL regularization term to align next dialogue act distributions with corpus-derived transition patterns to improve macro-F1 by 9–42% relative to encoders. |
| Outcome: | The proposed term improves macro-F1 by 9–42% relative to encoders and significantly improves dialogue-flow alignment. |
LLM-Codec: Neural Audio Codec Meets Language Model Objectives (2026.findings-acl)
Copied to clipboard
| Challenge: | Neural audio codecs are optimized for waveform reconstruction rather than autoregressive prediction. |
| Approach: | They propose to augment codec training with language-model-facing objectives while keeping both codec and LLM architectures unchanged. |
| Outcome: | The proposed model improves speech coherence and predictability by preserving the semantic alignment between audio and text representations. |
I0T: Embedding Standardization Method Towards Zero Modality Gap (2025.acl-long)
Copied to clipboard
| Challenge: | Recent studies on Contrastive Language-Image Pretraining suffer from a *modality gap* . modality gap occurs when image and text embeddings are projected to disparate manifolds . |
| Approach: | They propose a framework that reduces the modality gap by adding two normalization layers to each encoder. |
| Outcome: | The proposed framework reduces the modality gap while preserving the original embedding representations of trained models with their locked parameters. |
Tackling Long Code Search with Splitting, Encoding, and Aggregating (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing pretraining models take the first 256 tokens of code snippets by default, limiting the input length to 512. |
| Approach: | They propose a baseline SEA model which splits long code into code blocks and aggregates them to obtain a comprehensive long code representation. |
| Outcome: | The proposed model can model long code without changing their internal structure and re-pretraining. |
Beyond the Safety Tax: Mitigating Unsafe Text-to-Image Generation via External Safety Rectification (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing safety defenses typically intervene internally within the generative model, but suffer from severe concept entanglement, leading to degradation of benign generation quality. |
| Approach: | They propose a structurally isolated safety module that performs external, interpretable rectification without modifying the base model. |
| Outcome: | The proposed module performs external, interpretable rectification without modifying the base model. |
ToNER: Type-oriented Named Entity Recognition with Generative Language Model (2024.lrec-main)
Copied to clipboard
| Challenge: | Input too many potential entity types would distract the model inevitably. |
| Approach: | They propose to use a generative model to exploit entity types' merit on promoting NER task by appending a type matching model to identify the entity types most likely to appear in the sentence. |
| Outcome: | The proposed framework exploits entity types' merit on promoting NER task by adding auxiliary task to the model to discover the entity types. |
PseudoGD: Enhancing Spatial Reasoning in Vision-Language Models through Pseudo Geometric Knowledge Distillation (2026.findings-acl)
Copied to clipboard
| Challenge: | Recent Large Vision-Language Models (LVLMs) have shown remarkable success in general semantic understanding, but struggle with 3D spatial reasoning tasks. |
| Approach: | They propose a framework to help vision encoders internalize 3D geometric information using only standard 2D images. |
| Outcome: | The proposed framework achieves State-of-the-Art (SOTA) performance across various model architectures. |
ES4R: Speech Encoding Based on Prepositive Affective Modeling for Empathetic Response Generation (2026.acl-long)
Copied to clipboard
| Challenge: | Existing speech-to-speech large language models rely on ASR transcription or use encoders to extract latent representations, weakening affective information and contextual coherence in multi-turn dialogues. |
| Approach: | They propose a framework for speech-based empathetic response generation that captures turn-level affective states and dialogue-level emotional dynamics. |
| Outcome: | The proposed framework outperforms baselines in automatic and human evaluations and remains robust across different Large Language Model (LLM) backbones. |
Frozen LLMs are Native Decoders for High-Norm Semantic Vectors (2026.acl-long)
Copied to clipboard
| Challenge: | Existing compression methods selectively prune tokens based on information-theoretic metrics, resulting in interpretability but risking the loss of fine-grained information. |
| Approach: | They propose a landmark-based compression framework for long contexts that captures global dependencies over landmark tokens. |
| Outcome: | The proposed framework outperforms soft compression baselines on four QA benchmarks. |
Layer-wise Minimal Pair Probing Reveals Contextual Grammatical-Conceptual Hierarchy in Speech Representations (2025.emnlp-main)
Copied to clipboard
| Challenge: | a recent study evaluated the extent to which SLMs encode nuanced syntactic and conceptual features . acoustic and phonetic features are shallow, but the extent of nuance is unclear . |
| Approach: | a new study evaluates contextual syntactic and semantic features in transformer-based speech language models . authors compare SLMs to linguistic competence assessments for large language models. |
| Outcome: | a new study compares SLMs with linguistic competence assessments to assess speech recognition and understanding . the results show that SLM models encode grammatical features more robustly than conceptual ones . |
Adversarial Metric Learning for Fine-Grained Emotion Classification (2026.acl-long)
Copied to clipboard
| Challenge: | Recent advances in fine-grained emotion classification relied on contrastive learning with hard-pair mining. |
| Approach: | They propose an adversarial metric learning framework that replaces fixed similarity metrics with a learnable metric family and trains representations to remain discriminative under worst-case similarity distortions. |
| Outcome: | The proposed framework trains a pairwise discriminator to maximally confuse two hard pair types while training the encoder to remain discriminative under worst-case similarity distortions. |