SEMANTIC REPRESENTATION

CCG Parsing Algorithm with Incremental Tree Rotation (N19-1)

Challenge:	Event Extraction is a crucial yet arduous task in natural language processing (NLP), as its performance is hindered by laborious data annotation.
Approach:	They propose a Contrastive Event Aggregation Network with LLM-based Augmentation to promote low-resource learning and reduce data noise for event extraction.
Outcome:	The proposed approach achieves new state-of-the-art results on the ACE2005 and ERE-EN datasets.

Copied to clipboard

Miloš Stanojević, Mark Steedman

Challenge:	Combinatory Categorial Grammar (CCG) is a mildly context sensitive grammar formalism that excels in incremental sentence processing.
Approach:	They propose a new incremental parsing algorithm that uses a syntactic approach . it uses right-branching constituent structures and optional constituents that adjoin on the right .
Outcome:	The proposed algorithm can cover the whole CCGbank with greater incrementality and accuracy than previous proposals.

Can Uniform Meaning Representation Help GPT-4 Translate from Indigenous Languages? (2025.acl-short)

Copied to clipboard

Shira Wein

Hierarchical Curriculum Learning for AMR Parsing (2022.acl-short)

Challenge:	In this study, we examine the downstream utility of Uniform Meaning Representation (UMR) for low-resource languages.
Approach:	They explore the utility of Uniform Meaning Representation (UMR) for low-resource languages by incorporating it into GPT-4 prompts.
Outcome:	The proposed model performs better than existing models in Navajo, Arápaho, and Kukama with and without demonstrations and annotations.

Copied to clipboard

Peiyi Wang, Liang Chen, Tianyu Liu, Damai Dai, Yunbo Cao, Baobao Chang, Zhifang Sui

Semantic-based Pre-training for Dialogue Understanding (2022.coling-1)

Challenge:	Abstract Meaning Representation (AMR) parsing aims to translate sentences to semantic representation with a hierarchical structure, but there is a gap between their flat training objective and the hierarchic structure, which limits the model generalization.
Approach:	They propose a Hierarchical Curriculum Learning framework with Structure-level (SC) and Instance-level curricula (IC) that aims to translate sentences to semantic representation with a hierarchical structure.
Outcome:	Experiments on AMR2.0, AMR3.0, structure-complex and out-of-distribution situations confirm the effectiveness of the proposed framework.

Copied to clipboard

Xuefeng Bai, Linfeng Song, Yue Zhang

Additive Compositionality of Word Vectors (D19-55)

Challenge:	Pre-trained language models are weak in understanding the main semantic meaning of a dialogue context.
Approach:	They propose a semantic-based framework that leverages explicit semantic knowledge to capture the core semantic information in dialogues during pre-training.
Outcome:	The proposed model is superior to existing models on chit-chats and task-oriented dialogues.

Copied to clipboard

Yeon Seonwoo, Sungjoon Park, Dongkwan Kim, Alice Oh

Dialogue-AMR: Abstract Meaning Representation for Dialogue (2020.lrec-1)

Challenge:	Existing research on justifying additive compositionality of word embedding models requires a rather strong assumption of uniform word distribution.
Approach:	They propose to relax the assumption of uniform word distribution and propose more realistic conditions for proving additive compositionality.
Outcome:	The proposed model improves on word similarity and noisy sentence similarity.

Copied to clipboard

Claire Bonial, Lucia Donatelli, Mitchell Abrams, Stephanie M. Lukin, Stephen Tratz, Matthew Marge, Ron Artstein, David Traum, Clare Voss

AMUSED: A Multi-Stream Vector Representation Method for Use in Natural Dialogue (2020.lrec-1)

Challenge:	Abstract Meaning Representation (AMR) does not capture the illocutionary force or speaker’s intended contribution in the broader dialogue context.
Approach:	They propose a schema that enriches Abstract Meaning Representation (AMR) it provides a semantic representation for facilitating Natural Language Understanding (NLU) in dialogue systems.
Outcome:	The proposed schema provides a semantic representation for facilitating Natural Language Understanding (NLU) in human-robot dialogue systems.

Copied to clipboard

Gaurav Kumar, Rishabh Joshi, Jaspreet Singh, Promod Yenigalla

Pseudo Outlier Exposure for Out-of-Distribution Detection using Pretrained Transformers (2023.findings-acl)

Challenge:	Current architectures only take care of semantic and contextual information for a given query and fail to fully account for syntactic and external knowledge which are crucial for generating responses in a chit-chat system.
Approach:	They propose a multi-stream deep learning architecture that learns unified embeddings for query-response pairs by incorporating Graph Convolution Networks over their dependency parse.
Outcome:	The proposed architecture improves on the next sentence prediction task and significantly improves existing techniques.

Copied to clipboard

Jaeyoung Kim, Kyuheon Jung, Dongbin Na, Sion Jang, Eunbin Park, Sungchul Choi

Language Models

Challenge:	Existing methods to detect out-of-distribution (OOD) samples are overconfident for real-world language applications.
Approach:	They propose a method that constructs a surrogate OOD dataset by sequentially masking tokens related to ID classes.
Outcome:	The proposed method can train a rejection network with ID and diverse outlier samples but requires additional data collection overhead.

Cross-Lingual Abstract Meaning Representation Parsing (N18-1)

Copied to clipboard

Marco Damonte, Shay B. Cohen

Autoencoder as Assistant Supervisor: Improving Text Representation for Chinese Social Media Text Summarization (P18-2)

Challenge:	Abstract Meaning Representation (AMR) research has focused on English . Qualitative analysis shows that the new parsers overcome structural differences between the languages.
Approach:	They propose to use an AMR parser for English and parallel corpora to learn AMR for Italian, Spanish, German and Chinese.
Outcome:	The proposed method overcomes structural differences between the target languages and requires no gold standard data.

Copied to clipboard

Shuming Ma, Xu Sun, Junyang Lin, Houfeng Wang

SAC: Neural Speech Codec with Semantic-Acoustic Dual-Stream Quantization (2026.acl-long)

Challenge:	Existing abstractive text summarization models learn a semantic representation of the source text and the summaries from it.
Approach:	They evaluate the model on a popular Chinese social media dataset and compare it to other models.
Outcome:	The proposed model achieves state-of-the-art performance on a popular Chinese social media dataset.

Copied to clipboard

Wenxi Chen, Ruiqi Yan, Yushen Chen, Zhikang Niu, Ziyang Ma, Xiquan Li, Yuzhe Liang, null Wenhanlin, Shunshun Yin, Ming Tao, Xinsheng Wang, Xie Chen

Towards Open Environment Intent Prediction (2023.findings-acl)

Challenge:	Existing speech codecs struggle to balance high-quality reconstruction with semantically rich representations, limiting their effectiveness in both generative and understanding tasks.
Approach:	They propose a neural speech codec with semantic-acoustic dual-stream quantization that disentangles semantic and acousian modeling into two dedicated streams.
Outcome:	The proposed codec outperforms state-of-the-art speech tokenizers in auto-propagating text-to-speech models.

Copied to clipboard

Yunhua Zhou, Jiawei Hong, Xipeng Qiu

RetroMAE-2: Duplex Masked Auto-Encoder For Pre-Training Retrieval-Oriented Language Models (2023.acl-long)

Challenge:	Out-of-Domain (OOD) Intent Classification and New Intent Discovering are two tasks in the Task-Oriented Dialogue System.
Approach:	They propose a task paradigm to extend Out-of-Domain (OOD) Intent Classification and New Intent Discovering tasks in the Task-Oriented Dialogue System.
Outcome:	The proposed scheme improves on existing OOD intent classification and discovery datasets.

Copied to clipboard

Zheng Liu, Shitao Xiao, Yingxia Shao, Zhao Cao

Improving Gradient-based Adversarial Training for Text Classification by Contrastive Learning and Auto-Encoder (2021.findings-acl)

Challenge:	Existing methods for retrieval-oriented language models focus on contextualized embedding of the [CLS] token, but recent study shows that ordinary tokens besides [CLL] may provide extra information, which help to produce a better representation effect.
Approach:	They propose a method where all contextualized embeddings of pre-trained model can be jointly pre-trained for retrieval tasks.
Outcome:	The proposed method improves the quality of representation where all contextualized embeddings of the pre-trained model can be leveraged.

Copied to clipboard

Yao Qiu, Jinchao Zhang, Jie Zhou

Meaning to Form: Measuring Systematicity as Information (P19-1)

Challenge:	Recent work has shown that models can be easily fooled by intentionally designed adversarial examples.
Approach:	They propose two efficient approaches for generating adversarial perturbations on embeddings and propose two new approaches to help model learn adversarials more efficiently.
Outcome:	The proposed approaches outperform strong baselines on various text classification datasets and the model's performance drops less under adversarial attack.

Copied to clipboard

Tiago Pimentel, Arya D. McCarthy, Damian Blasi, Brian Roark, Ryan Cotterell

Challenge:	A longstanding debate in semiotics centers on the relationship between linguistic signs and their corresponding semantics: is there an arbitrary relationship between word forms and their meaning, or does some systematic phenomenon pervade?
Approach:	They propose to quantify the systematicity of the sign using mutual information and recurrent neural networks to examine 106 languages.
Outcome:	The proposed model reduces entropy in a word form conditioned on its semantic representation and recovers English examples of systematic affixes.

Knowledge Enhanced Fine-Tuning for Better Handling Unseen Entities in Dialogue Generation (2021.emnlp-main)

Copied to clipboard

Leyang Cui, Yu Wu, Shujie Liu, Yue Zhang

Landmark Embedding: A Chunking-Free Embedding Method For Retrieval Augmented Long-Context Large Language Models (2024.acl-long)

Challenge:	Existing methods for dialogue generation use an external knowledge base to generate appropriate responses.
Approach:	They propose to use an external knowledge base to generate appropriate responses for unseen entities.
Outcome:	Experiments on two dialogue corpus show that pre-trained models perform poorly with unseen entities.

Copied to clipboard

Kun Luo, Zheng Liu, Shitao Xiao, Tong Zhou, Yubo Chen, Jun Zhao, Kang Liu

Learning Shared Semantic Space for Speech-to-Text Translation (2021.findings-acl)

Challenge:	Existing methods for retrieval augmentation work with chunked contexts, which leads to poor quality of semantic representation and incomplete retrieval of useful information.
Approach:	They propose a method for retrieval augmentation of long-context language modeling using landmark embedding.
Outcome:	The proposed method outperforms existing retrieval methods with a notable advantage.

Copied to clipboard

Chi Han, Mingxuan Wang, Heng Ji, Lei Li

Text Generation

Challenge:	End-to-end speech translation (ST) has been treated as an independent task . however, the modality gap has rendered MT data and its end-to end models incompatible with their ST counterparts.
Approach:	They propose to bridge the representation gap between text and audio inputs by projecting audio and text features to a common semantic representation.
Outcome:	The proposed model improves performance on two ST benchmarks and achieves 27.1 BLEU on MuST-C EN-DE.

Integrating Semantic Scenario and Word Relations for Abstractive Sentence Summarization (2021.emnlp-main)

Copied to clipboard

Yong Guan, Shaoru Guo, Ru Li, Xiaoli Li, Hu Zhang

BERT-BC: A Unified Alignment and Interaction Model over Hierarchical BERT for Response Selection (2024.lrec-main)

Challenge:	Existing graph-based methods only consider word relations or structure information, which neglect the correlation between them.
Approach:	They propose a Dual Graph network for Abstractive Sentence Summarization that captures word relations and structure information from sentences.
Outcome:	The proposed model outperforms state-of-the-art methods on two popular benchmark datasets.

Copied to clipboard

Zhenfei Yang, Beiming Yu, Yuan Cui, Shi Feng, Daling Wang, Yifei Zhang

Dialogue Systems & Conversational Agents

Challenge:	Recent performance boosting for dialogue response selection task achieved by Cross-Encoder based models is limited and the learned models have poor generalization capability in realistic scenarios.
Approach:	They propose a model that combines the representation-based Bi-Encoder and interaction-based Cross-Encoding to achieve better semantic representation.
Outcome:	The proposed model can achieve state-of-the-art performance on three benchmark datasets for multi-turn response selection.

CLIO: Role-interactive Multi-event Head Attention Network for Document-level Event Extraction (2022.coling-1)

Copied to clipboard

Yubing Ren, Yanan Cao, Fang Fang, Ping Guo, Zheng Lin, Wei Ma, Yi Liu

I Know What You Asked: Graph Path Learning using AMR for Commonsense Reasoning (2020.coling-main)

Challenge:	Existing methods for document-level event extraction struggle due to two intrinsic challenges: nested arguments and multiple events.
Approach:	They propose a role-interactive multi-event head attention network to solve two challenges . they map different events to multiple subspaces and then determine whether the current event exists .
Outcome:	The proposed model improves on two widely used DEE datasets on the Internet.

Copied to clipboard

Jungwoo Lim, Dongsuk Oh, Yoonna Jang, Kisu Yang, Heuiseok Lim

Reasoning

Challenge:	a large amount of pre-defined commonsense knowledge is available for commonsensense reasoning . humans acquire commonsence in their lives, but machines cannot learn commonseense without assistance.
Approach:	They propose an AMR-ConceptNet-Pruned (ACP) graph that is pruned from a full integrated graph . they show that the ACP graph interprets the reasoning path and predicts the correct answer .
Outcome:	The proposed graph outperforms baseline models in the commonsenseQA task . it shows that the reasoning path can be interpreted with the relations and concepts provided by the graph .

Neural Text Generation from Rich Semantic Representations (N19-1)

Copied to clipboard

Valerie Hajdik, Jan Buys, Michael Wayne Goodman, Emily M. Bender

Representation Learning

Challenge:	2 is a neural model that maps a linearization of Dependency MRS to text . 1 is based on a BLEU score of 66.11 when trained on gold data .
Approach:	They propose to use Minimal Recursion Semantics to generate high-quality text from structured representations.
Outcome:	The proposed model achieves a BLEU score of 77.17 on the full test set and 83.37 on the subset of test data most closely matching the silver data domain.

AMR-DA: Data Augmentation by Abstract Meaning Representation (2022.findings-acl)

Copied to clipboard

Ziyi Shou, Yuxin Jiang, Fangzhen Lin

Taming Pre-trained Language Models with N-gram Representations for Low-Resource Domain Adaptation (2021.acl-long)

Challenge:	Abstract Meaning Representation (AMR) is a semantic representation for NLP/NLU.
Approach:	They propose to use AMR-DA for data augmentation in NLP . they use sentence-level techniques like back translation and token-level methods like EDA .
Outcome:	The proposed method outperforms EDA and AEDA and improves on STS and text classification tasks.

Copied to clipboard

Shizhe Diao, Ruijia Xu, Hongjin Su, Yilei Jiang, Yan Song, Tong Zhang

AMR-TST: Abstract Meaning Representation-based Text Style Transfer (2023.findings-acl)

Challenge:	Existing methods to train pre-trained models require domain-specific data and computational resources.
Approach:	They propose a domain-aware N-gram Adaptor to incorporate unseen and domain-specific words into a generic pretrained model.
Outcome:	The proposed model can improve on eight low-resource tasks using limited data with lower computational costs.

Copied to clipboard

Kaize Shi, Xueyao Sun, Li He, Dingxian Wang, Qing Li, Guandong Xu

Semantics as a Foreign Language (D18-1)

Challenge:	Abstract Meaning Representation (AMR) is a semantic representation that can enhance natural language generation (NLG) by providing a logical semantic input.
Approach:	They propose an AMR-based text style transfer technique that converts source text to an AML graph and generates transferred text based on the AMR graph modified by a TST policy named style rewriting.
Outcome:	The proposed method achieves state-of-the-art results compared with baseline models in automatic and human evaluations.

Copied to clipboard

Gabriel Stanovsky, Ido Dagan

Structured Data in NLP

Challenge:	(2017): Syntactic grammars capture propositions, but graph-based representations aim to capture a wider notion of propositions.
Approach:	They propose a neural sequence-to-sequence framework which can recover syntactic linearizations by a sequence-based approach.
Outcome:	The proposed framework performs almost on-par with previous state-of-the-art approaches while requiring less parallel training annotations.

Original Semantics-Oriented Attention and Deep Fusion Network for Sentence Matching (D19-1)

Copied to clipboard

Mingtong Liu, Yujie Zhang, Jinan Xu, Yufeng Chen

Challenge:	Sentence matching is a key issue in natural language inference and paraphrase identification.
Approach:	They propose a semantics-oriented attention and deep fusion network (OSOA-DFN) that is oriented to the original semantic representation of another sentence and propagates attention information at each matching layer.
Outcome:	The proposed model can model sentence matching more precisely on three sentence matching benchmark datasets.

Domain Adapted Distant Supervision for Pedagogically Motivated Relation Extraction (2020.lrec-1)

Copied to clipboard

Oscar Sainz, Oier Lopez de Lacalle, Itziar Aldabe, Montse Maritxalar

Text Generation Model Enhanced with Semantic Information in Aspect Category Sentiment Analysis (2023.findings-acl)

Challenge:	Existing systems for question generation based on shallow linguistic information at text level generate questions for reading comprehension.
Approach:	They propose a relation extraction system that extracts pedagogically motivated relation types from a text to generate questions for reading comprehension.
Outcome:	The proposed system extracts pedagogically motivated relations from a text . it performs better on the subset of relations suitable for pedagical purposes.

Copied to clipboard

Tu Tran, Kiyoaki Shirai, Natthawut Kertkeidkachorn

Are AI-Generated Text Detectors Robust to Adversarial Perturbations? (2024.acl-long)

Challenge:	Existing methods for ACSA fail to model relations of target words and opinion words in a sentence including multiple aspects.
Approach:	They propose to incorporate AMR into a text generation model to model relations of target words and opinion words in a sentence including multiple aspects.
Outcome:	The proposed method outperforms state-of-the-art methods on three datasets.

Copied to clipboard

Guanhua Huang, Yuchen Zhang, Zhe Li, Yongjian You, Mingze Wang, Zhouwang Yang

Robustness in NLP

Challenge:	Existing detectors for AI-generated text lack robustness against adversarial perturbations, with even minor changes in characters or words causing a reversal in distinguishing between human-created and AI-generated text.
Approach:	They propose a siamese calibration technique to train the model to make equally confident predictions under different noise, which improves the model’s robustness against adversarial perturbations.
Outcome:	The proposed detector outperforms baseline methods on four datasets and is more generalizable in cross-domain, cross-genre, and mixed-source scenarios.

Word Sense Disambiguation with Knowledge-Enhanced and Local Self-Attention-based Extractive Sense Comprehension (2022.coling-1)

Copied to clipboard

Guobiao Zhang, Wenpeng Lu, Xueping Peng, Shoujin Wang, Baoshuo Kan, Rui Yu

A Two-Level Interpretation of Modality in Human-Robot Dialogue (2020.coling-main)

Challenge:	Word sense disambiguation (WSD) is one of the most challenging tasks in natural language processing.
Approach:	They propose a method to extract the right sense from a sentence context . they propose to incorporate additional examples and definitions of related senses in WordNet .
Outcome:	The proposed method achieves better performance than baseline models on public benchmark datasets.

Copied to clipboard

Lucia Donatelli, Kenneth Lai, James Pustejovsky

Region under Discussion for visual dialog (2021.emnlp-main)

Challenge:	modal expressions are used to communicate and align world knowledge, but there is no obvious manner to ground them in the shared environment.
Approach:	They propose a two-level annotation scheme for modality that captures both content and intent and a task-oriented, pragmatic representation that maps to our robot's capabilities.
Outcome:	The proposed model can be grounded and dynamically interpreted.

Copied to clipboard

Mauricio Mazuecos, Franco M. Luque, Jorge Sánchez, Hernán Maina, Thomas Vadora, Luciana Benotti

SEA-BED: How Do Embedding Models Represent Southeast Asian Languages? (2026.acl-long)

Challenge:	Visual Dialog is assumed to require the dialog history to generate correct responses during a dialog.
Approach:	They propose an interpretable representation that visually grounds dialog history by constraining the image’s spatial features according to a semantic representation inspired by Question under Discussion.
Outcome:	The proposed representation constrains the image’s spatial features according to a semantic representation of the history inspired by the information structure notion of Question under Discussion.

Copied to clipboard

Wuttikorn Ponwitayarat, Peerat Limkonchotiwat, Raymond Ng, Jann Railey Montalan, Thura Aung, Jian Gang Ngui, Yosephine Susanto, William Chandra Tjhi, Panuthep Tasawong, Erik Cambria, Ekapol Chuangsuwanich, Sarana Nutanong

Representation Learning

Challenge:	SEA-BED examines how multilingual text embeddings perform across tasks and languages . performance gaps arise from data coverage, training objectives, and architectural design, authors say .
Approach:	They propose a large-scale benchmark covering 10 SEA languages and diverse embedding tasks.
Outcome:	The proposed model performs poorly across languages and tasks, but language-task analyses reveal inconsistencies . the results suggest that performance gaps arise from limitations in data coverage, training objectives, and architectural design.

Conversational Semantic Parsing (2020.emnlp-main)

Copied to clipboard

Armen Aghajanyan, Jean Maillard, Akshat Shrivastava, Keith Diedrick, Michael Haeger, Haoran Li, Yashar Mehdad, Veselin Stoyanov, Anuj Kumar, Mike Lewis, Sonal Gupta

Dialog Intent Structure: A Hierarchical Schema of Linked Dialog Acts (L18-1)

Challenge:	Structured representations for task-oriented assistant systems are limited due to the limitations of the representation.
Approach:	They propose a semantic representation for task-oriented conversational systems that can represent co-reference and context carryover.
Outcome:	The proposed model improves the best results on ATIS, SNIPS, TOP and DSTC2 by up to 5 points for slot-carryover.

Copied to clipboard

Silvia Pareti, Tatiana Lando

Dialogue Systems & Conversational Agents

Challenge:	a schema for dialog representation captures the pragmatic intents of the conversation independently from any semantic representation.
Approach:	They propose a hierarchical and extensible schema for dialog representation . schema captures pragmatic intents of conversation independently from any semantic representation based on semantic content .
Outcome:	The proposed schema captures the pragmatic intents of the conversation independently from any semantic representation.

Extracting Shopping Interest-Related Product Types from the Web (2023.findings-acl)

Copied to clipboard

Yinghao Li, Colin Lockard, Prashant Shiralkar, Chao Zhang

A Neural Citation Count Prediction Model based on Peer Review Text (D19-1)

Challenge:	Existing e-commerce products are limited in their ability to assist customers in interest-oriented shopping.
Approach:	They propose to extract PTs from Web pages containing hand-crafted PT recommendations for SIs . they propose to use tree-transformer encoders for node classification to improve inter-node dependency modeling .
Outcome:	The proposed model outperforms the best baseline model by 2.37 F1 points on a WebPT dataset.

Copied to clipboard

Siqing Li, Wayne Xin Zhao, Eddy Jing Yin, Ji-Rong Wen

Scene Graph Modification as Incremental Structure Expanding (2022.coling-1)

Challenge:	Recent studies have focused on extracting or mining useful features from the paper itself or the associated authors.
Approach:	They propose to utilize peer review data for the CCP task with a neural prediction model to learn a comprehensive semantic representation for peer review text.
Outcome:	The proposed model improves on the peer review data and hand-crafted features.

Copied to clipboard

Xuming Hu, Zhijiang Guo, Yu Fu, Lijie Wen, Philip S. Yu

Using Structured Content Plans for Fine-grained Syntactic Control in Pretrained Language Model Generation (2022.coling-1)

Challenge:	Scene graphs are used in cross-modal tasks such as image retrieval, image captioning, and visual question answering.
Approach:	They propose a model that iterates between nodes prediction and edges prediction . they frame scene graph modification as a graph expansion task by introducing incremental structure expanding .
Outcome:	The proposed model surpasses the state-of-the-art model by large margins on four benchmarks.

Copied to clipboard

Fei-Tzin Lee, Miguel Ballesteros, Feng Nan, Kathleen McKeown

Visual Information Guided Zero-Shot Paraphrase Generation (2022.coling-1)

Challenge:	Large pretrained language models can generate powerful text but cannot be controlled at a sub-sentential level.
Approach:	They propose to make such fine-grained control possible in pretrained LMs by generating text directly from a semantic representation, Abstract Meaning Representation (BART), which is augmented at the node level with syntactic control tags.
Outcome:	The proposed method can generate text from a semantic representation, which is augmented at the node level with syntactic control tags.

Copied to clipboard

Zhe Lin, Xiaojun Wan

Text Generation

Challenge:	Several studies use different information as ”pivot” such as language, semantic representation and so on.
Approach:	They propose to use visual information as the "pivot" of back-translation to generate paraphrases using paired image-caption data.
Outcome:	The proposed model generates paraphrase with good relevancy, fluency and diversity . it is based on paired image-caption data and can train a paraphrasing model .

Beyond Distribution: Investigating Language Models’ Understanding of Sino-Korean Morphemes (2025.findings-emnlp)

Copied to clipboard

Taehee Jeon

Language Models

Challenge:	Transformer-based language models can learn compositional morphology of SK morphemes . morphological models trained on Hangul text can learn SK, but performance is based on frequency of words .
Approach:	They investigate whether Transformer-based language models can learn compositional morphology of Sino-Korean morphemes.
Outcome:	The proposed models learn the compositional morphology of SK morphemes from real and fake pairs.

Can Large Language Models Interpret Noun-Noun Compounds? A Linguistically-Motivated Study on Lexicalized and Novel Compounds (2024.acl-long)

Copied to clipboard

Giulia Rambelli, Emmanuele Chersoni, Claudia Collacciani, Marianna Bolognesi

Multi-step Reasoning via Recurrent Dual Attention for Visual Dialog (P19-1)

Challenge:	Noun-noun compounds represent an important challenge for Natural Language Understanding . correct interpretation of noun-nomin compounds is essential for many applications .
Approach:	They test whether Large Language Models can interpret the semantic relation between nouns . they also test whether they can abstract from such knowledge to predict the relation .
Outcome:	The proposed models can interpret the semantic relation between nouns and compounds using analogical comparisons.

Copied to clipboard

Zhe Gan, Yu Cheng, Ahmed Kholy, Linjie Li, Jingjing Liu, Jianfeng Gao

LDIR: Low-Dimensional Dense and Interpretable Text Embeddings with Relative Representations (2025.findings-acl)

Challenge:	Existing models for visual dialog infer the answer through multiple reasoning steps.
Approach:	They propose a model for visual dialog that uses multi-step reasoning to answer questions about an image.
Outcome:	The proposed model achieves a new state-of-the-art of 64.47% on the VisDial v1.0 dataset .

Copied to clipboard

Yile Wang, Zhanyu Shen, Hui Huang

Explainability & Interpretability in NLP

Challenge:	Existing text embeddings with high dimensions are difficult to trace and interpret.
Approach:	They propose low-dimensional and interpretable text embeddings with relative representations that encode semantic meanings in a vector space where similar texts are close together in the representation space.
Outcome:	The proposed embeddings outperform existing models on multiple tasks with fewer dimensions and are lowdimensional and dense while maintaining interpretability.

See Detail Say Clear: Towards Brain CT Report Generation via Pathological Clue-driven Representation Learning (2024.findings-emnlp)

Copied to clipboard

Chengxin Zheng, Junzhong Ji, Yanzhao Shi, Xiaodan Zhang, Liangqiong Qu

Model-Agnostic Cross-Lingual Training for Discourse Representation Structure Parsing (2024.lrec-main)

Challenge:	Brain CT report generation is important to aid physicians in diagnosing cranial diseases.
Approach:	They propose a Pathological Clue-driven Representation Learning model to build cross-modal representations based on pathological clues and adapt them for text generation.
Outcome:	The proposed method outperforms previous methods and achieves SoTA performance.

Copied to clipboard

Jiangming Liu

gMBA: Expression Semantic Guided Mixed Boolean-Arithmetic Deobfuscation Using Transformer Architectures (2025.findings-acl)

Challenge:	Discourse Representation Structure (DRS) parsers are constrained when trained exclusively on monolingual data.
Approach:	They propose a cross-lingual training strategy that leverages cross-linguistic training data to train models in multiple languages.
Outcome:	The proposed method improves clause and graph parsing in English, German, Italian and Dutch.

Copied to clipboard

Youjeong Roh, Joon-Young Paik, Jingun Kwon, Eun-Sun Cho

Learning to Look at the Other Side: A Semantic Probing Study of Word Embeddings in LLMs with Enabled Bidirectional Attention (2025.acl-long)

Challenge:	Mixed Boolean-Arithmetic (MBA) obfuscation protects intellectual property by converting programs into complex forms that are difficult to analyze.
Approach:	They propose a mixed-boolean-arithmetic (MBA) obfuscation framework that transforms a Transformer-based neural encoder-decoder into a truth table that is an automatically constructed semantic representation of an expression's behavior.
Outcome:	The proposed framework improves performance and highlights the importance of internal semantic expressions in recovering obfuscated code to its original form.

Copied to clipboard

Zhaoxin Feng, Jianfei Ma, Emmanuele Chersoni, Xiaojing Zhao, Xiaoyi Bao

ZeLa: Advancing Zero-Shot Multilingual Semantic Parsing with Large Language Models and Chain-of-Thought Strategies (2024.lrec-main)

Challenge:	Autoregressive Large Language Models (LLMs) demonstrate exceptional performance in language understanding and generation tasks, but their application in text embedding tasks has been relatively slow due to the constraints of the unidirectional attention mechanism.
Approach:	They propose to enable bidirectional attention in LLMs to improve their ability to represent subsequent context but weaken their utilization of preceding context.
Outcome:	The proposed model improves the LLMs’ ability to represent subsequent context but weakens their utilization of preceding context, while contrastive learning training can help to maintain both abilities.

Copied to clipboard

Truong Dinh Do, Phuong Minh Nguyen, Minh Nguyen

Flow-Based Page Unique Semantic Mapping Architecture for Document Visual Question Answering (2026.acl-long)

Challenge:	Existing approaches to augment multilingual datasets with labeled English data are lacking in annotated data.
Approach:	They propose a framework to augment English data and then use it to train parsers . they propose to use multilingual chain-of-thought prompting techniques to augment other languages' data .
Outcome:	The proposed framework augments English data in other languages and trains them with no demonstration samples in target languages.

Copied to clipboard

Haosen Wang, Jing Xiao, Chaochao Du, Xiaowang Zhang, Zhiyong Feng