DECODERS

HydraSum: Disentangling Style Features in Text Summarization with Multi-Decoder Models (2022.emnlp-main)

Challenge:	Constrained decoding algorithms produce hypotheses satisfying all constraints, but they are computationally expensive and can lower the generated text quality.
Approach:	They propose a Mention Flag mechanism which traces whether lexical constraints are satisfied in outputs of an S2S decoder.
Outcome:	The proposed models maintain higher constraint satisfaction and text quality than baseline models and other constrained decoding algorithms.

Copied to clipboard

Tanya Goyal, Nazneen Rajani, Wenhao Liu, Wojciech Kryscinski

Summarization

Challenge:	Abstractive summarization systems implicitly encode “decisions” about summary properties, but these are not enforced.
Approach:	They propose a new summarization architecture that extends existing models to a mixture-of-experts version with multiple decoders.
Outcome:	The proposed architecture outperforms baseline models in obtaining stylistically-diverse summaries by sampling from individual decoders or their mixtures.

Representing Numbers in NLP: a Survey and a Vision (2021.naacl-main)

Copied to clipboard

Avijit Thawani, Jay Pujara, Filip Ilievski, Pedro Szekely

Multimodality

Challenge:	Numeracy is an essential skill for language understanding since numbers are often interspersed in text.
Approach:	They propose a comprehensive taxonomy of tasks and methods to represent numbers in text . they synthesize best practices for representing numbers in texts and articulate a vision for holistic numeracy .
Outcome:	The proposed model synthesizes best practices for representing numbers in text . it argues that the model is more effective than other approaches .

De-Biased Court’s View Generation with Causality (2020.emnlp-main)

Copied to clipboard

Yiquan Wu, Kun Kuang, Yating Zhang, Xiaozhong Liu, Changlong Sun, Jun Xiao, Yueting Zhuang, Luo Si, Fei Wu

The Shape of Learning: Anisotropy and Intrinsic Dimensions in Transformer-Based Models (2024.findings-eacl)

Challenge:	Existing approaches to court’s view generation can be used to address this problem, but neglecting the confounding bias in data can limit the model performance and pollute learning outcomes.
Approach:	They propose a novel Attentional and Counterfactual based Natural Language Generation method consisting of an attentional encoder and a pair of innovative counterfactual decoders to generate judgment-discriminative court's views.
Outcome:	The proposed method is able to generate judgment-discriminative court's views (both supportive and non-supportive views) under both quantitative and qualitative evaluation metrics.

Copied to clipboard

Anton Razzhigaev, Matvey Mikhalchuk, Elizaveta Goncharova, Ivan Oseledets, Denis Dimitrov, Andrey Kuznetsov

Coarse-to-Fine Decoding for Neural Semantic Parsing (P18-1)

Challenge:	Embeddings in transformers encode vast amounts of linguistic nuances and patterns.
Approach:	They investigate the anisotropy dynamics and intrinsic dimension of embeddings in transformers . they found that transformer decoders exhibit a bell-shaped anisotropie profile .
Outcome:	The investigated embeddings exhibit a bell-shaped curve with the highest anisotropy concentrations in the middle layers . the intrinsic dimension increases in the initial phases of training, indicating an expansion into higher-dimensional space.

Copied to clipboard

Li Dong, Mirella Lapata

Language Models for German Text Simplification: Overcoming Parallel Data Scarcity through Style-specific Pre-training (2023.findings-acl)

Challenge:	Experimental results show that semantic parsing is more efficient than using simple decoders.
Approach:	They propose a structure-aware neural architecture which decomposes the semantic parsing process into two stages.
Outcome:	The proposed architecture consistently improves performance on four datasets characteristic of different domains and meaning representations.

Copied to clipboard

Miriam Anschütz, Joshua Oehms, Thomas Wimmer, Bartłomiej Jezierski, Georg Groh

Joint Entity Extraction and Assertion Detection for Clinical Text (P19-1)

Challenge:	Existing methods to train automatic text simplification systems for languages other than English are limited by the lack of parallel data.
Approach:	They propose to use German Easy Language as a corpus of automatic text simplification systems to fine-tune language models to the style characteristics of the language.
Outcome:	The proposed language models adapt to the style characteristics of Easy Language and output more accessible texts.

Copied to clipboard

Parminder Bhatia, Busra Celikkaya, Mohammed Khalilia

Online Back-Parsing for AMR-to-Text Generation (2020.emnlp-main)

Challenge:	Existing systems for in-formation extraction treat negative medical findings as a pipeline of two separate tasks.
Approach:	They propose a multi-task neural model to jointly extract entities and negations from medical reports.
Outcome:	The proposed model performs considerably better than existing systems on a 2010 i2b2/VA challenge dataset and a proprietary de-identified clinical dataset.

Copied to clipboard

Xuefeng Bai, Linfeng Song, Yue Zhang

Syntactically Supervised Transformers for Faster Neural Machine Translation (P19-1)

Challenge:	Abstract meaning representation (AMR) is a semantic graph representation that abstracts meaning away from a sentence.
Approach:	They propose a decoder that back predicts projected AMR graphs on target sentences . their results show superiority over previous state-of-the-art decoded graph Transformer .
Outcome:	The proposed model outperforms the state-of-the-art model on two AMR benchmarks.

Copied to clipboard

Nader Akoury, Kalpesh Krishna, Mohit Iyyer

Encoders Help You Disambiguate Word Senses in Neural Machine Translation (D19-1)

Challenge:	Standard decoders for neural machine translation generate a single token per timestep, which slows inference . a series of controlled experiments demonstrates that SynST decodes sentences 5x faster than the baseline autoregressive Transformer.
Approach:	They propose a syntactically supervised Transformer that generates all target tokens in one shot . synST is a variant of the Transformer architecture that autoregressively predicts a chunked parse tree .
Outcome:	The proposed method decodes sentences 5x faster than the baseline method on En-De and En-Fr datasets while achieving higher BLEU scores.

Copied to clipboard

Gongbo Tang, Rico Sennrich, Joakim Nivre

A Hierarchical Latent Structure for Variational Conversation Modeling (N18-1)

Challenge:	Neural machine translation models can perform word sense disambiguation (WSD) however, it is unclear which component dominates the process of disambiguating words.
Approach:	They evaluate hidden states and investigate distributions of self-attention in NMT encoders and decoders to disambiguate word senses.
Outcome:	The proposed model outperforms encoder hidden states on large datasets . the model outpersforms decoders on large data sets .

Copied to clipboard

Yookoon Park, Jaemin Cho, Gunhee Kim

Dialogue Systems & Conversational Agents

Challenge:	Variational autoencoders suffer from the notorious degeneration problem, according to a new study . utterance drop regularization is an important feature of the hierarchical RNNs .
Approach:	They propose a variational hierarchical conversation RNN framework that exploits latent variables and an utterance drop regularization to exploit latent variable.
Outcome:	The proposed model outperforms state-of-the-art models on Cornell Movie Dialog and Ubuntu Dialog Corpus.

Syntax-Infused Variational Autoencoder for Text Generation (P19-1)

Copied to clipboard

Xinyuan Zhang, Yi Yang, Siyang Yuan, Dinghan Shen, Lawrence Carin

Syntactic Text Processing

Challenge:	Experimental results demonstrate the generative superiority of SIVAE on both reconstruction and targeted syntactic evaluations.
Approach:	They propose a syntax-infused variational autoencoder that integrates sentences with their syntactic trees to improve the grammar of generated sentences.
Outcome:	The proposed model improves the grammar of generated sentences by integrating sentences with syntactic trees.

ZeroAE: Pre-trained Language Model based Autoencoder for Transductive Zero-shot Text Classification (2023.findings-acl)

Copied to clipboard

Kaihao Guo, Hang Yu, Cong Liao, Jianguo Li, Haipeng Zhang

Low-Resource NLP

Challenge:	Existing methods for text classification use only encoders or decoders that do not allow for the use of labels in unseen domains.
Approach:	They propose an autoencoder that encodes text into two disentangled spaces and decodes it to generate text with labels in the unseen domains.
Outcome:	The proposed model outperforms the existing methods in label-partially-unseen and label-fully-un-seeen scenarios and even outperfects the SOTA methods.

Recursive Top-Down Production for Sentence Generation with Latent Trees (2020.findings-emnlp)

Copied to clipboard

Shawn Tan, Yikang Shen, Alessandro Sordoni, Aaron Courville, Timothy J. O’Donnell

Streaming Models for Joint Speech Recognition and Translation (2021.eacl-main)

Challenge:	Various studies have shown that incorporating syntactic structures into recursive encoders can be beneficial for various natural language tasks.
Approach:	They propose a dynamic programming algorithm that marginalises over latent binary tree structures with N leaves to train a recursive neural function.
Outcome:	The proposed model outperforms previous models on the LENGTH split and English question formation tasks on the Multi30k dataset.

Copied to clipboard

Orion Weller, Matthias Sperber, Christian Gollan, Joris Kluivers

Breaking Down Multilingual Machine Translation (2022.findings-acl)

Challenge:	Using end-to-end models for speech translation has become a focus of the ST community . cascaded models have the advantage of including automatic speech recognition output .
Approach:	They propose a model that condenses sound waves into translated text and integrates automatic speech recognition outputs into the models.
Outcome:	The proposed model is statistically similar to cascading models, but has half the number of parameters.

Copied to clipboard

Ting-Rui Chiang, Yi-Pei Chen, Yi-Ting Yeh, Graham Neubig

Multilinguality

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.

Improving English-Arabic Transliteration with Phonemic Memories (2022.findings-emnlp)

Copied to clipboard

Yuanhe Tian, Renze Lou, Xiangyu Pang, Lianxi Wang, Shengyi Jiang, Yan Song

Challenge:	Existing neural approaches to transliterate names from English to Arabic are limited and focus on leveraging the phonemic association between English and Arabic.
Approach:	They propose a model for English-Arabic transliteration using a memory module modeling the phonemic association between English and Arabic to guide the transliterations process.
Outcome:	The proposed model improves on EANames corpus, which better represents names in the general public than linked Wikipedia entries that are always names of famous people.

On Difficulties of Cross-Lingual Transfer with Order Differences: A Case Study on Dependency Parsing (N19-1)

Copied to clipboard

Wasi Ahmad, Zhisong Zhang, Xuezhe Ma, Eduard Hovy, Kai-Wei Chang, Nanyun Peng

Cross-Lingual Transfer

Challenge:	Existing studies on crosslingual transfer have focused on word-level information sharing, but words are not independent in sentences; their combinations form larger linguistic units, known as context.
Approach:	They propose to use orderagnostic models to transfer word order to distant languages . they train dependency parsers on an English corpus and evaluate their transfer performance on 30 other languages.
Outcome:	The proposed model performs better on languages with different word orders than on other languages.

Modelling Context Emotions using Multi-task Learning for Emotion Controlled Dialog Generation (2021.eacl-main)

Copied to clipboard

Deeksha Varshney, Asif Ekbal, Pushpak Bhattacharyya

Dialogue Systems & Conversational Agents

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.

A Span-level Bidirectional Network for Aspect Sentiment Triplet Extraction (2022.emnlp-main)

Copied to clipboard

Yuqi Chen, Chen Keming, Xian Sun, Zequn Zhang

Sentiment Analysis

Challenge:	Aspect Sentiment Triplet Extraction (ASTE) is a new fine-grained sentiment analysis task . recent studies have focused on solving aspects term extraction, opinion term extraction and aspect-level sentiment classification tasks individually or in combination of two subtasks.
Approach:	They propose a span-level bidirectional network which utilizes all possible spans as input and extracts triplets from spans bidirectionally.
Outcome:	The proposed framework outperforms state-of-the-art methods and improves performance . it can extract triplets of aspect terms, sentiments, and opinion terms from review sentences .

Multilingual Unsupervised NMT using Shared Encoder and Language-Specific Decoders (P19-1)

Copied to clipboard

Sukanta Sen, Kamal Kumar Gupta, Asif Ekbal, Pushpak Bhattacharyya

Multilinguality

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.

Dual-decoder Transformer for Joint Automatic Speech Recognition and Multilingual Speech Translation (2020.coling-main)

Copied to clipboard

Hang Le, Juan Pino, Changhan Wang, Jiatao Gu, Didier Schwab, Laurent Besacier

Keeping Consistency of Sentence Generation and Document Classification with Multi-Task Learning (D19-1)

Challenge:	Existing models for automatic speech recognition and multilingual speech translation are on par with cascade counterparts.
Approach:	They propose a dual-decoder Transformer architecture that performs automatic speech recognition and multilingual speech translation.
Outcome:	The proposed models outperform the previously-reported highest translation performance in multilingual settings and bilingual one-to-one results.

Copied to clipboard

Toru Nishino, Shotaro Misawa, Ryuji Kano, Tomoki Taniguchi, Yasuhide Miura, Tomoko Ohkuma

Comparison of Conventional Hybrid and CTC/Attention Decoders for Continuous Visual Speech Recognition (2024.lrec-main)

Challenge:	Existing automated generation of articles' characteristics is inconsistent if they are generated individually.
Approach:	They propose a multi-task learning model with a shared encoder and multiple decoders for each task.
Outcome:	The proposed model generates more consistent headlines, key phrases and categories . it outperforms baseline model on the ROUGE scores and generates fluent headlines .

Copied to clipboard

David Gimeno-Gómez, Carlos-D. Martínez-Hinarejos

Multimodality

Challenge:	Recent advances have been achieved in Visual Speech Recognition (VSR) despite the lack of data, there is no clear comparison between different types of decoders for certain languages and tasks.
Approach:	They focused on how the conventional DNN-HMM decoder behaves depending on the amount of data used for their estimation.
Outcome:	The proposed model improves the CTC/Attention model in data-scarcity scenarios while requiring less training time and fewer parameters.

SparseFlow: Accelerating Transformers by Sparsifying Information Flows (2024.acl-long)

Copied to clipboard

Yeachan Kim, SangKeun Lee

Let’s Ask Again: Refine Network for Automatic Question Generation (D19-1)

Challenge:	SparseFlow is an efficient method to sparsify the dense information flows within transformers.
Approach:	They propose a method to sparsify the dense pathways of token representations across all transformer blocks by parameterizing them to be sparse.
Outcome:	The proposed method reduces computational costs by half on average without compromising task accuracy.

Copied to clipboard

Preksha Nema, Akash Kumar Mohankumar, Mitesh M. Khapra, Balaji Vasan Srinivasan, Balaraman Ravindran

Modularized Multilingual NMT with Fine-grained Interlingua (2024.naacl-long)

Challenge:	Existing AQG models produce incomplete questions which look like incomplete drafts with scope for refinement.
Approach:	They propose a method which mimics the human process of generating questions by first creating an initial draft and then refining it.
Outcome:	The proposed method outperforms state-of-the-art methods on three datasets and improves on fluency and answerability metrics.

Copied to clipboard

Sungjun Lim, Yoonjung Choi, Sangha Kim

Conjoin after Decompose: Improving Few-Shot Performance of Named Entity Recognition (2024.lrec-main)

Challenge:	Neural Machine Translation (MNMT) systems lack layer-sharing to generate interlingua features . however, layer-share structure does not guarantee explicit propagation of language-specific features to respective decoders.
Approach:	They propose to share top of language-specific encoder layers to enable interlingua features . their method demonstrates an improved average BLEU score by "+2.90" in En-to-Any directions .
Outcome:	The proposed approach improves the BLEU score by "+2.90" in En-to-Any directions and by "+1.06" in zero-shot translation.

Copied to clipboard

Chengcheng Han, Renyu Zhu, Jun Kuang, Fengjiao Chen, Xiang Li, Ming Gao, Xuezhi Cao, Yunsen Xian

Information Extraction & Text Mining

Challenge:	Existing prompt-based NER models fail to detect entity boundaries, causing performance degradation.
Approach:	They propose a model which consists of a BART encoder and a parabiotic decoder and propose ' boundary expansion strategy' to enhance the model's capability in entity type classification.
Outcome:	The proposed model can achieve significant performance gains over state-of-the-art models.

Decomposable Neural Paraphrase Generation (P19-1)

Copied to clipboard

Zichao Li, Xin Jiang, Lifeng Shang, Qun Liu

Sequence Repetition Enhances Token Embeddings and Improves Sequence Labeling with Decoder-only Language Models (2026.findings-eacl)

Challenge:	Existing models learn to generate paraphrases by mapping a sequence to another, with each word processed and generated in a uniform way.
Approach:	They propose a Transformer-based model that can learn and generate paraphrases at different levels of granularity in a disentangled way.
Outcome:	The proposed model achieves competitive in-domain performance compared to state-of-the-art models and significantly better performance when adapting to a new domain.

Copied to clipboard

Matija Luka Kukić, Marko Čuljak, David Dukić, Martin Tutek, Jan Šnajder

AEG: Argumentative Essay Generation via A Dual-Decoder Model with Content Planning (2022.emnlp-main)

Challenge:	Modern language models (LMs) are trained in autoregressive manner, conditioned on the prefix. sequence labeling (SL) tasks assign labels to each individual input token, naturally benefiting from bidirectional context.
Approach:	They explore sequence repetition (SR) as a less invasive alternative to decoder-only models . they show that increasing the number of repetitions does not degrade SL performance .
Outcome:	The proposed technique improves the quality of token-level embeddings and surpasses encoders and unmasked decoders.

Copied to clipboard

Jianzhu Bao, Yasheng Wang, Yitong Li, Fei Mi, Ruifeng Xu

AdaTag: Multi-Attribute Value Extraction from Product Profiles with Adaptive Decoding (2021.acl-long)

Challenge:	Existing studies on argument generation focus on generating individual short arguments, while research on generating long and coherent argumentative essays is under-explored.
Approach:	They propose a task to automatically generate argumentative essays using a writing prompt.
Outcome:	The proposed model generates persuasive essays with higher diversity and less repetition compared to baselines.

Copied to clipboard

Jun Yan, Nasser Zalmout, Yan Liang, Christan Grant, Xiang Ren, Xin Luna Dong

AGRec: Adapting Autoregressive Decoders with Graph Reasoning for LLM-based Sequential Recommendation (2025.findings-acl)

Challenge:	Existing approaches to extract product attribute values are limited by knowledge sharing across different attributes.
Approach:	They propose to use adaptive decoding to handle extraction of product attribute values by parameterizing the decoder with pretrained attribute embeddings, through a hypernetwork and a Mixture-of-Experts module.
Outcome:	The proposed model is able to handle multiple attributes without sharing the entire network parameters across all attributes.

Copied to clipboard

Xinfeng Wang, Jin Cui, Fumiyo Fukumoto, Yoshimi Suzuki

Structured Data in NLP

Challenge:	Autoregressive decoders in large language models excel at capturing sequential behaviors for generative recommendations, but they lack graph-structured user-item interactions, which are widely recognized as beneficial.
Approach:	They propose a novel algorithm that adapts LLMs’ decoders with graph reasoning for recommendation by augmenting the decoding logits with an auxiliary GNN model to optimize token generation.
Outcome:	The proposed model outperforms state-of-the-art models in sequential recommendations.

StereoRel: Relational Triple Extraction from a Stereoscopic Perspective (2021.acl-long)

Copied to clipboard

Xuetao Tian, Liping Jing, Lu He, Feng Liu

Information Extraction & Text Mining

Challenge:	Existing methods for relational triple extraction still face challenges, including information loss and error propagation.
Approach:	They propose a model which maps relational triples to a three-dimensional space and leverages three decoders to extract them.
Outcome:	The proposed model outperforms the baselines on five public datasets.

Direct Simultaneous Speech-to-Text Translation Assisted by Synchronized Streaming ASR (2021.findings-acl)

Copied to clipboard

Junkun Chen, Mingbo Ma, Renjie Zheng, Liang Huang

Multitasking Framework for Unsupervised Simple Definition Generation (2022.acl-long)

Challenge:	Existing approaches to simultaneous speech-to-text translation suffer from error propagation and extra latency.
Approach:	They propose a new paradigm for simultaneous speech-to-text translation using two separate decoders . they use multitask learning to jointly learn these two tasks with a shared encoder .
Outcome:	The proposed method achieves substantially better translation quality at similar levels of latency.

Copied to clipboard

Cunliang Kong, Yun Chen, Hengyuan Zhang, Liner Yang, Erhong Yang

Responsible & Trustworthy NLP

Challenge:	Existing definition generation tasks require a dictionary with complex definitions and a corpus containing arbitrary simple texts to generate them.
Approach:	They propose a multitasking framework SimpDefiner that only requires a standard dictionary with complex definitions and a corpus containing arbitrary simple texts.
Outcome:	The proposed framework outperforms the baseline model by a 1.77 SARI score on the English dataset, and raises the proportion of the low level (HSK level 1-3) words in Chinese definitions by 3.87%.

On the Sub-layer Functionalities of Transformer Decoder (2020.findings-emnlp)

Copied to clipboard

Yilin Yang, Longyue Wang, Shuming Shi, Prasad Tadepalli, Stefan Lee, Zhaopeng Tu

Focus Attention: Promoting Faithfulness and Diversity in Summarization (2021.acl-long)

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.

Copied to clipboard

Rahul Aralikatte, Shashi Narayan, Joshua Maynez, Sascha Rothe, Ryan McDonald

Summarization

Challenge:	Currently, document summarization is challenging even for humans.
Approach:	They propose a focus attention mechanism which encourages decoders to generate tokens that are topically similar to the input document.
Outcome:	The proposed method outperforms top-k and nucleus sampling methods on the BBC extreme summarization task and is more accurate than focus attention-based models.

Cross-Lingual Abstractive Summarization with Limited Parallel Resources (2021.acl-long)

Copied to clipboard

Yu Bai, Yang Gao, Heyan Huang

On Parsing as Tagging (2022.emnlp-main)

Challenge:	Existing approaches to cross-lingual summarization use limited available cross-linguistic resources.
Approach:	They propose a multi-task framework for cross-lingual abstractive summarization that uses a single decoder to generate monolingual and cross-linguistic summaries.
Outcome:	Experiments on two CLS datasets show that the proposed model outperforms baseline models in low-resource and full-dataset scenarios.

Copied to clipboard

Afra Amini, Ryan Cotterell

Syntactic Text Processing

Challenge:	Existing approaches to reduce constituency parsing to tagging are based on linearization, learning, and decoding . linearization of the derivation tree is the most critical factor in achieving accurate parsers as taggers .
Approach:	They propose a pipeline with three steps for reducing constituency parsing to tagging . they find that linearization and learning are critical factors for accurate parsers .
Outcome:	The proposed pipelines are linearized, learning, and decoded, and have three steps to achieve accurate parsing as taggers.

Collaborative Learning of Bidirectional Decoders for Unsupervised Text Style Transfer (2021.emnlp-main)

Copied to clipboard

Yun Ma, Yangbin Chen, Xudong Mao, Qing Li

Low-Resource NLP

Challenge:	Existing methods for unsupervised text style transfer struggle to achieve high style conversion rate and low content loss.
Approach:	They propose a collaborative learning framework for unsupervised text style transfer using a pair of bidirectional decoders.
Outcome:	The proposed framework achieves strong empirical results on style compatibility and content preservation.

Towards Unified Spoken Language Understanding Decoding via Label-aware Compact Linguistics Representations (2023.findings-acl)

Copied to clipboard

Zhihong Zhu, Xuxin Cheng, Zhiqi Huang, Dongsheng Chen, Yuexian Zou

Biomed-Enriched: Data-Efficient Biomedical Pretraining via Paragraph-Level Annotation (2026.findings-acl)

Challenge:	Existing methods for intent detection and slot filling decoders could result in misaligned predictions for both tasks.
Approach:	They propose a method that leverages label embeddings to jointly guide the decoding process.
Outcome:	The proposed method outperforms existing methods on two single- and multi-intent SLU benchmarks and can be incorporated into existing models.

Copied to clipboard

Rian Touchent, Nathan Godey, Éric Villemonte de la Clergerie