SEMANTIC REPRESENTATIONS

Span-based Joint Entity and Relation Extraction with Attention-based Span-specific and Contextual Semantic Representations (2020.coling-main)

Challenge:	Existing methods for semantic parsing use placeholders to represent relations between sentences and semantic representations.
Approach:	They show that compositional parsers can remember unbounded number of placeholders . this is the first study of this kind to describe relations between sentences and semantic representations based on projective mechanisms.
Outcome:	The proposed method can represent relations between sentences and semantic representations without using nonprojective mechanisms.

Copied to clipboard

Bin Ji, Jie Yu, Shasha Li, Jun Ma, Qingbo Wu, Yusong Tan, Huijun Liu

Integrating Generative Lexicon Event Structures into VerbNet (L18-1)

Challenge:	Existing methods treat each span token equally important, ignoring significant features.
Approach:	They propose a span-based joint extraction framework with attention-based semantic representations that utilizes span-specific and contextual representations.
Outcome:	The proposed model outperforms existing models on ACE2005, CoNLL2004 and ADE.

Copied to clipboard

Susan Windisch Brown, James Pustejovsky, Annie Zaenen, Martha Palmer

Challenge:	Efforts to use the verb lexicon's semantic representations have revealed a need to revise the form to allow for greater flexibility in representing complex events.
Approach:	They propose to restrict the form to first-order representations to simplify use by planners and integrate with the Generative Lexicon's event structure.
Outcome:	The proposed representations simplify use by and integration with planners and allow for greater flexibility in representing complex events and for a more nuanced portrayal of the Agent's role.

Natural Language Generation: Recently Learned Lessons, Directions for Semantic Representation-based Approaches, and the Case of Brazilian Portuguese Language (P19-2)

Copied to clipboard

Marco Antonio Sobrevilla Cabezudo, Thiago Pardo

Representation Learning

Challenge:	Natural Language Generation (NLG) is a promising area in Natural Language Processing (NLP) .
Approach:	They present a review of the literature on Natural Language Generation in Brazilian Portuguese.
Outcome:	The proposed approaches are based on the Abstract Meaning Representation formalism and have potential future directions.

Back-Translation as Strategy to Tackle the Lack of Corpus in Natural Language Generation from Semantic Representations (D19-63)

Copied to clipboard

Marco Antonio Sobrevilla Cabezudo, Simon Mille, Thiago Pardo

Learning Negation Scope from Syntactic Structure (2020.starsem-1)

Challenge:	Abstract Meaning Representation and Brazilian Portuguese (BP) are selected as semantic representation and language, respectively.
Approach:	They propose to use Brazilian Portuguese and Abstract Meaning Representation as semantic representations for NLG.
Outcome:	The proposed methods were evaluated on two datasets (one automatically generated and another human-generated) to compare the performance in a real context.

Copied to clipboard

Nick McKenna, Mark Steedman

Syntactic Text Processing

Challenge:	a semi-supervised model learns the semantics of negation purely through syntactic analysis . Negation is a semantic phenomenon in natural language which varies significantly .
Approach:	They propose a semi-supervised model which learns negation semantics purely through syntactic analysis.
Outcome:	The proposed model achieves state-of-the-art on a Negation Scope Detection task without identifying individual words or extracting features beyond syntax.

Exploring Semantic Spaces for Detecting Clustering and Switching in Verbal Fluency (2022.coling-1)

Copied to clipboard

Özge Alacam, Simeon Schüz, Martin Wegrzyn, Johanna Kißler, Sina Zarrieß

Text Clustering

Challenge:	Existing evaluations of word/concept representations on verbal fluency tasks rely on human annotations of clusters and switches between sub-categories.
Approach:	They analyze word/concept representations in an experimental verbal fluency dataset . they find that ConceptNet embeddings outperforms other semantic representations .
Outcome:	The proposed method outperforms other semantic representations by a large margin.

SeaEval for Multilingual Foundation Models: From Cross-Lingual Alignment to Cultural Reasoning (2024.naacl-long)

Copied to clipboard

Bin Wang, Zhengyuan Liu, Xin Huang, Fangkai Jiao, Yang Ding, AiTi Aw, Nancy Chen

Multilinguality

Challenge:	a new benchmark for multilingual foundation models is being developed . brittleness of foundation models in the dimensions of semantics and multilinguality is a key limitation .
Approach:	They propose a benchmark for multilingual foundation models, SeaEval . they examine how well these models comprehend cultural practices, nuances, and values .
Outcome:	The proposed model can be used to evaluate multilingual and multicultural scenarios.

Logographic Information Aids Learning Better Representations for Natural Language Inference (2022.findings-aacl)

Copied to clipboard

Zijian Jin, Duygu Ataman

GeoGround: Uncertainty-Weighted Multi-Task Learning for Geo-Alignment and Address Defect Detection (2026.acl-industry)

Challenge:	Statistical language models often ignore information related to logographic features of written text . many languages, including Chinese and Vietnamese, use logographic writing systems .
Approach:	They propose to provide language models with logographic information to learn better semantic representations.
Outcome:	The proposed model improves semantic representations in six languages with logographic writing systems.

Copied to clipboard

Srinivas Virinchi, Aman Gulati, Anoop Saladi

VisDoT : Enhancing Visual Reasoning through Human-Like Interpretation Grounding and Decomposition of Thought (2026.findings-eacl)

Challenge:	Address intelligence in e-commerce requires precise geocoding and proactive defect detection under strict sub-50 ms latency constraints.
Approach:	They propose a multi-task learning framework that jointly models coordinate grounding and address defect detection.
Outcome:	The proposed model achieves 5.86 gains in address defect detection precision and 4.86 improvements in location prediction accuracy over strong encoder baselines while remaining 75 more efficient than decoder LLMs such as Qwen2-1.5B.

Copied to clipboard

Eunsoo Lee, Jeongwoo Lee, Minki Hong, Jangho Choi, Jihie Kim

Explainability & Interpretability in NLP

Challenge:	Lack of perceptual grounding limits vision-language models' ability to interpret visual data . prior work on visualized data understanding focused on adapting VLMs to instruction tuning and chain-of-thought supervision .
Approach:	They propose a framework that enhances visual reasoning through human-like interpretation grounding.
Outcome:	The proposed framework improves on ChartQA and ChartQAPro benchmarks by +11.2%.

Logical Inferences with Comparatives and Generalized Quantifiers (2020.acl-srw)

Copied to clipboard

Izumi Haruta, Koji Mineshima, Daisuke Bekki

Textual Inference

Challenge:	Comparative constructions pose a challenge in Natural Language Inference (NLI) Comparatives interact with quantifiers, numerals, and lexical antonyms, but a logical inference system for comparatives has not been developed for the task.
Approach:	They propose a compositional semantics system that maps comparative constructions to semantic representations via combinatory categorial grammar parsers and integrates it with an automated theorem proving system.
Outcome:	The proposed system outperforms previous logic-based systems and deep learning models on three NLI datasets.

Automatic Derivation of Semantic Representations for Thai Serial Verb Constructions: A Grammar-Based Approach (2024.acl-srw)

Copied to clipboard

Vipasha Bansal

Representation Learning

Challenge:	Using rich semantic representations for Thai Serial Verb Constructions (SVCs) is time-consuming and manual annotation is preferred.
Approach:	They propose to implement an HPSG analysis for Thai Serial Verb Constructions (SVCs) they use a DELPH-IN computational grammar to generate appropriate representations from syntactic features.
Outcome:	The proposed grammar increases verified coverage of Thai SVCs by 73% and decreases ambiguity by 46% on held-out data.

Fine-tuning Pre-trained Language Models for Few-shot Intent Detection: Supervised Pre-training and Isotropization (2022.naacl-main)

Copied to clipboard

Haode Zhang, Haowen Liang, Yuwei Zhang, Li-Ming Zhan, Xiao-Ming Wu, Xiaolei Lu, Albert Lam

Language Models

Challenge:	Recent studies show that fine-tuning pre-trained language models with a small set of labeled utterances in a supervised manner is helpful, but it yields an anisotropic feature space, which may suppress the expressive power of the semantic representations.
Approach:	They propose to regularize supervised pre-training towards isotropy by contrastive learning and correlation matrix regularizers.
Outcome:	The proposed methods improve supervised pre-training by regularizing the feature space towards isotropy.

Unsupervised Learning of Sentence Embeddings Using Compositional n-Gram Features (N18-1)

Copied to clipboard

Matteo Pagliardini, Prakhar Gupta, Martin Jaggi

Fine-grained Contrastive Learning for Definition Generation (2022.aacl-main)

Challenge:	Currently, unsupervised word embeddings are routinely trained on large amounts of raw text data.
Approach:	They propose to use unsupervised word embeddings to train distributed representations of sentences.
Outcome:	The proposed method outperforms state-of-the-art models on most benchmark tasks and is robust to the produced general-purpose sentence embeddings.

Copied to clipboard

Hengyuan Zhang, Dawei Li, Shiping Yang, Yanran Li

An Auto-Encoder Matching Model for Learning Utterance-Level Semantic Dependency in Dialogue Generation (D18-1)

Challenge:	Recent pre-trained transformer-based definition generation models lack effective representation learning to contain full semantic components of the given word, leading to under-specific definitions.
Approach:	They propose a novel contrastive learning method that encourages the model to capture more detailed semantic representations from the definition sequence encoding.
Outcome:	The proposed method could generate more specific definitions compared with state-of-the-art models.

Copied to clipboard

Liangchen Luo, Jingjing Xu, Junyang Lin, Qi Zeng, Xu Sun

Dialogue Systems & Conversational Agents

Challenge:	Experimental results show that our model can generate semantically coherent responses compared to baseline models.
Approach:	They propose an Auto-Encoder Matching model to learn utterance-level semantic dependency . their model contains two auto-encoders and one mapping module .
Outcome:	Experimental results show that the proposed model can generate high coherence and fluency compared to baseline models.

Constrained Decoding for Neural NLG from Compositional Representations in Task-Oriented Dialogue (P19-1)

Copied to clipboard

Anusha Balakrishnan, Jinfeng Rao, Kartikeya Upasani, Michael White, Rajen Subba

Word Representation Learning in Multimodal Pre-Trained Transformers: An Intrinsic Evaluation (2021.tacl-1)

Challenge:	Generating fluent natural language responses from structured semantic representations is a critical step in task-oriented conversational systems.
Approach:	They propose using tree-structured semantic representations for better discourse-level structuring and sentence-level planning and introduce a challenging dataset using this representation for the weather domain.
Outcome:	The proposed model improves discourse-level structuring and sentence-level planning on a weather domain and can be decoded to improve semantic correctness.

Copied to clipboard

Sandro Pezzelle, Ece Takmaz, Raquel Fernández

Corpus of Chinese Dynastic Histories: Gender Analysis over Two Millennia (2020.lrec-1)

Challenge:	Existing models for linguistic representations of words are based on information extracted from large text corpora, and the sensory-motor experiences humans have with the world play an important role in determining word meaning.
Approach:	They propose to use contextualized word representations to learn semantic representations of words that align with human semantic intuitions.
Outcome:	The proposed models are shown to be more efficient on concrete word pairs than on abstract ones.

Copied to clipboard

Sergey Zinin, Yang Xu

Challenge:	Chinese dynastic histories form a long continuous linguistic space of approximately 2000 years . there is no freely available corpus of these histories, making Classical Chinese low-resource.
Approach:	a project introduces an open-source corpus of twenty-four dynastic histories covered by a Creative Commons license.
Outcome:	a new open-source corpus of 20 dynastic histories is developed for analysis of historical linguistic use of male and female terms.

Robust Question Answering Through Sub-part Alignment (2021.naacl-main)

Copied to clipboard

Jifan Chen, Greg Durrett

Robustness in NLP

Challenge:	Current textual question answering models fail to generalize to out-of-domain settings.
Approach:	They propose to decompose question and context into smaller units and align them to find the answer.
Outcome:	The proposed model is more robust than the standard BERT QA model on adversarial and out-of-domain datasets.

Unsupervised Discrete Sentence Representation Learning for Interpretable Neural Dialog Generation (P18-1)

Copied to clipboard

Tiancheng Zhao, Kyusong Lee, Maxine Eskenazi

The Emergence of Semantics in Neural Network Representations of Visual Information (N18-2)

Challenge:	Existing encoder-decoder dialog models cannot output interpretable actions as in traditional systems.
Approach:	They propose an unsupervised discrete sentence representation learning method that integrates with existing encoder-decoder dialog models for interpretable response generation.
Outcome:	The proposed model can be integrated with existing encoder-decoder dialog models and discover interpretable semantics via either auto encoding or context predicting.

Copied to clipboard

Dhanush Dharmaretnam, Alona Fyshe

Visual Data in NLP

Challenge:	Convolutional neural networks learn about semantics through corpora, but they must be shared . a recent study shows that concepts exist independently of language .
Approach:	They employ techniques previously used to detect semantic representations in the human brain to detect representations of CNNs.
Outcome:	The proposed techniques could be used to combat adversarial attacks on CNNs, the authors say .

Tagging-Assisted Generation Model with Encoder and Decoder Supervision for Aspect Sentiment Triplet Extraction (2023.emnlp-main)

Copied to clipboard

Luo Xianlong, Meng Yang, Yihao Wang

A Psycholinguistic Analysis of BERT’s Representations of Compounds (2023.eacl-main)

Challenge:	Recent advances in the ASTE task have been driven by Natural Language Generation-based approaches, but most NLG methods overlook the supervision of the encoder-decoder hidden representations and fail to fully utilize the semantic information provided by the labels.
Approach:	They propose a tagging-assisted generation model with encoder and decoder supervision that enhances the supervision of the encoder-decoder through multiple-perspective tabbing assistance and label semantic representations.
Outcome:	The proposed model enhances the supervision of the encoder and decoder through multiple-perspective tagging assistance and label semantic representations.

Copied to clipboard

Lars Buijtelaar, Sandro Pezzelle

LSTMEmbed: Learning Word and Sense Representations from a Large Semantically Annotated Corpus with Long Short-Term Memories (P19-1)

Challenge:	'compound' semantic representations are based on the semantics of constituent words, and are lexical items like any other word.
Approach:	They leverage a dataset that includes human judgments on two psycholinguistic measures of compound semantic analysis: lexeme meaning dominance (LMD) and semantic transparency (ST).
Outcome:	The proposed representations are based on a dataset that includes human judgments on two psycholinguistic measures of compound semantic analysis: lexeme meaning dominance (LMD) and semantic transparency (ST).

Copied to clipboard

Ignacio Iacobacci, Roberto Navigli

ScalingFilter: Assessing Data Quality through Inverse Utilization of Scaling Laws (2024.emnlp-main)

Challenge:	Recent work has focused on vector representations which capture different meanings, i.e., senses, of words.
Approach:	They propose a bidirectional LSTM model which learns word senses from semantically annotated corpora by focusing on word order.
Outcome:	The proposed model achieves state-of-the-art on the SemEval-2014 word-to-sense similarity task and is available online at http://lcl.uniroma1.it/LSTMEmbed.

Copied to clipboard

Ruihang Li, Yixuan Wei, Miaosen Zhang, Nenghai Yu, Han Hu, Houwen Peng

Question Generation Using Sequence-to-Sequence Model with Semantic Role Labels (2023.eacl-main)

Challenge:	Existing quality filtering methods rely on a high-quality dataset as reference . Existing methods introduce potential biases and compromise diversity .
Approach:	They propose a method that evaluates text quality based on the perplexity difference between two language models trained on the same data.
Outcome:	The proposed approach improves performance of pre-trained models without increasing training costs.

Copied to clipboard

Alireza Naeiji, Aijun An, Heidar Davoudi, Marjan Delpisheh, Muath Alzghool

Analyzing the Role of Semantic Representations in the Era of Large Language Models (2024.naacl-long)

Challenge:	Existing question generation methods that generate multiple questions from text are labor-intensive and do not capture the complexity of ways a human asks questions.
Approach:	They propose a question generation method that combines the benefits of rule-based and neural sequence-to-sequence (Seq2Sequen) models.
Outcome:	The proposed method significantly improves the state-of-the-art neural question generation approaches on three real-world data sets.

Copied to clipboard

Zhijing Jin, Yuen Chen, Fernando Gonzalez Adauto, Jiarui Liu, Jiayi Zhang, Julian Michael, Bernhard Schölkopf, Mona Diab

uFACT: Unfaithful Alien-Corpora Training for Semantically Consistent Data-to-Text Generation (2022.findings-acl)

Challenge:	Existing studies show the benefits of semantic representations in NLP tasks . Existing work using AMR is concerned with trainable models .
Approach:	They propose an AMR-driven chain-of-thought prompting method that uses AMR . they propose to use it to predict which input examples AMR may help or hurt on .
Outcome:	The proposed method hurts performance more than it helps on five different tasks.

Copied to clipboard

Tisha Anders, Alexandru Coca, Bill Byrne

SpanProto: A Two-stage Span-based Prototypical Network for Few-shot Named Entity Recognition (2022.emnlp-main)

Challenge:	uFACT (Un-Faithful Alien Corpora Training) is a training corpus construction method for data-to-text generation models.
Approach:	They propose a training corpus construction method for data-to-text (d2t) generation models which augments a target corpus with alien corpora which have different semantic representations.
Outcome:	The proposed method generates utterances which represent the semantic content of the data sources more accurately compared to models trained on the target corpus alone.

Copied to clipboard

Jianing Wang, Chengyu Wang, Chuanqi Tan, Minghui Qiu, Songfang Huang, Jun Huang, Ming Gao

Tailor: Generating and Perturbing Text with Semantic Controls (2022.acl-long)

Challenge:	Existing methods for few-shot Named Entity Recognition ignore entity boundaries and are time-consuming . a seminal span-based prototypical network solves the problem using two stages: span extraction and mention classification.
Approach:	They propose a seminal span-based prototypical network that tackles few-shot NER . they transform sequential tags into a global boundary matrix and use prototypical learning .
Outcome:	The proposed model outperforms strong baselines over multiple benchmarks.

Copied to clipboard

Alexis Ross, Tongshuang Wu, Hao Peng, Matthew Peters, Matt Gardner

Challenge:	Existing studies train task-specific generators, relying on training a model for every perturbation.
Approach:	They propose a semantically-controlled text generation system that modifies sentences to match target attributes.
Outcome:	The proposed system produces textual outputs conditioned on control codes derived from semantic representations.

Revisiting Document Representations for Large-Scale Zero-Shot Learning (2021.naacl-main)

Copied to clipboard

Jihyung Kil, Wei-Lun Chao

Deciphering Rumors: A Multi-Task Learning Approach with Intent-aware Hierarchical Contrastive Learning (2024.emnlp-main)

Challenge:	Existing methods for visual recognition use visual attributes carefully annotated by humans.
Approach:	They propose a semi-automatic mechanism for visual sentence extraction that leverages document section headers and clustering structure of visual sentences.
Outcome:	The proposed method improves on the ImageNet dataset with 10,000 unseen classes.

Copied to clipboard

Chang Yang, Peng Zhang, Hui Gao, Jing Zhang

Language Tags Matter for Zero-Shot Neural Machine Translation (2021.findings-acl)

Challenge:	Social networks are rife with noise and misleading information, presenting multifaceted challenges for rumor detection.
Approach:	They propose a new multi-task learning framework that mines latent intentions and rumor semantic features . they propose to use event-level and intent-level strategies to establish cognitive anchors .
Outcome:	The proposed framework improves the effectiveness of rumor detection and addresses the challenges present in the field.

Copied to clipboard

Liwei Wu, Shanbo Cheng, Mingxuan Wang, Lei Li

Multilinguality

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.

Abstract Meaning Representation of Constructions: The More We Include, the Better the Representation (L18-1)

Copied to clipboard

Claire Bonial, Bianca Badarau, Kira Griffitt, Ulf Hermjakob, Kevin Knight, Tim O’Gorman, Martha Palmer, Nathan Schneider

Massive vs. Curated Embeddings for Low-Resourced Languages: the Case of Yorùbá and Twi (2020.lrec-1)

Challenge:	Abstract Meaning Representation (AMR) uses a flexible pattern or template of multiple lexical items to provide semantic representation of certain constructions.
Approach:	They propose to expand the AMR project's lexicon of predicate senses to include entries for a growing set of constructions.
Outcome:	The proposed approach provides coverage for the annotation of certain types of constructions.

Copied to clipboard

Jesujoba Alabi, Kwabena Amponsah-Kaakyire, David Adelani, Cristina España-Bonet

Definition generation for lexical semantic change detection (2024.findings-acl)

Challenge:	a recent study shows that word embeddings can be useful for training downstream natural language processing tasks.
Approach:	They compare word embeddings obtained by word embeds from curated corpora with a language-dependent processing.
Outcome:	The proposed model compares word embeddings with word embeds from curated corpora and a language-dependent processing on two African languages.

Copied to clipboard

Mariia Fedorova, Andrey Kutuzov, Yves Scherrer

Challenge:	a number of studies have attempted to bridge the gap between lexical semantic change detection and sense-based LSCD methods.
Approach:	They propose a sense distribution based LSCD method which uses contextualized word definitions as 'senses' they argue that the method preserves interpretability and allows to inspect the reasons behind a specific shift in terms of discrete definitions-as-sense.
Outcome:	The proposed method outperforms previous sense-based methods on five datasets and three languages and preserves interpretability and allows to inspect the reasons behind a specific shift in terms of discrete definitions-as-senses.

Revisiting Pivot-Based Paraphrase Generation: Language Is Not the Only Optional Pivot (2021.emnlp-main)

Copied to clipboard

Yitao Cai, Yue Cao, Xiaojun Wan

A Parser for LTAG and Frame Semantics (L18-1)

Challenge:	Existing methods for paraphrase generation rely on language as the pivot . however, there is no evidence that parallel data of paraphrases is needed for paraphrasing.
Approach:	They propose to use semantic and syntactic representations as pivot for paraphrase generation.
Outcome:	The proposed method can generate paraphrases with better quality than using language as pivot.

Copied to clipboard

David Arps, Simon Petitjean

Challenge:	Existing parsers for Lexicalized Tree Adjoining Grammars and frame semantics are difficult to use due to the size of the resources to develop.
Approach:	They propose a parser which uses Lexicalized Tree Adjoining Grammars and frame semantics to combine them.
Outcome:	The proposed grammars are based on Lexicalized Tree Adjoining Grammars and frame semantics.

Does Vision-and-Language Pretraining Improve Lexical Grounding? (2021.findings-emnlp)

Copied to clipboard

Tian Yun, Chen Sun, Ellie Pavlick

Data Augmentation with Atomic Templates for Spoken Language Understanding (D19-1)

Challenge:	Large pretrained language models (LMs) have been criticized for lack of grounding, i.e., connecting words to their meanings in the physical world.
Approach:	They compare vision-and-language (VL) models trained jointly on text and image or video data to find out how they compare to text-only counterparts.
Outcome:	The proposed model outperforms the text-only variants on a commonsense question answering task.

Copied to clipboard

Zijian Zhao, Su Zhu, Kai Yu

Low-Resource NLP

Challenge:	Existing methods to enlarge SLU data require large amounts of labelled data.
Approach:	They propose a data augmentation method with atomic templates for Spoken Language Understanding which generates atomic exemplars from atomic template.
Outcome:	The proposed method improves on a DSTC 2&3 dataset which is a domain adaptation setting of SLU.

BERT Meets CTC: New Formulation of End-to-End Speech Recognition with Pre-trained Masked Language Model (2022.findings-emnlp)

Copied to clipboard

Yosuke Higuchi, Brian Yan, Siddhant Arora, Tetsuji Ogawa, Tetsunori Kobayashi, Shinji Watanabe

Language Models

Challenge:	Existing approaches to connectionist temporal classification (CTC) are based on pre-trained language models (LMs)
Approach:	They propose a formulation of connectionist temporal classification that relaxes the conditional independence assumptions used in conventional CTC and incorporates linguistic knowledge through explicit output dependency.
Outcome:	The proposed model improves over conventional approaches across variations in speaking styles and languages while maintaining CTC’s training efficiency.

Linguistic representations for fewer-shot relation extraction across domains (2023.acl-long)

Copied to clipboard

Sireesh Gururaja, Ritam Dutt, Tinglong Liao, Carolyn Rosé

Dscorer: A Fast Evaluation Metric for Discourse Representation Structure Parsing (2020.acl-main)

Challenge:	Recent work has demonstrated the positive impact of incorporating linguistic representations as additional context and scaffolds on performance in several NLP tasks.
Approach:	They extend previous work to examine whether linguistic representations enhance generalizability . they incorporate syntactic and semantic graphs from off-the-shelf tools into a transformer-based architecture .
Outcome:	The proposed approach enhances generalization by providing cross-domain pivots . it also shows that syntactic and semantic graphs exhibit roughly equivalent utility .

Copied to clipboard

Jiangming Liu, Shay B. Cohen, Mirella Lapata

Would you describe a leopard as yellow? Evaluating crowd-annotations with justified and informative disagreement (2020.coling-main)

Challenge:	Discourse representation structures (DRSs) are scoped semantic representations for texts of arbitrary length.
Approach:	They propose a new metric which converts box-style DRSs to graphs and measures the overlap of n-grams.
Outcome:	Experiments show that Dscorer computes accuracy scores that are correlated with Counter at a fraction of the time.

Copied to clipboard

Pia Sommerauer, Antske Fokkens, Piek Vossen

Challenge:	Existing evaluation methods rely on agreement between annotators, which implies a single correct interpretation.
Approach:	They propose an agreement-independent quality metric based on answer-coherence to evaluate on expected disagreement.
Outcome:	The proposed model shows that agreement is the most important indicator of quality in semantic annotation tasks.

A Semantic Distance Metric Learning approach for Lexical Semantic Change Detection (2024.findings-acl)

Copied to clipboard

Taichi Aida, Danushka Bollegala

SMedBERT: A Knowledge-Enhanced Pre-trained Language Model with Structured Semantics for Medical Text Mining (2021.acl-long)

Challenge:	Existing Word-in-Context (WiC) datasets are used to detect temporal semantic changes of words.
Approach:	They propose a supervised two-staged SCD method that uses existing Word-in-Context (WiC) datasets to predict temporal semantic changes of words.
Outcome:	The proposed method achieves strong performance in multiple languages and significant improvements on WiC benchmarks.

Copied to clipboard

Taolin Zhang, Zerui Cai, Chengyu Wang, Minghui Qiu, Bite Yang, Xiaofeng He

Distilling Large Embeddings via Hyperspherical Householder Quantization (2026.acl-long)

Challenge:	Existing knowledge-based PLMs are based on linked-entity information, but they only use linked-enemy information as auxiliary information.
Approach:	They propose to integrate semantic knowledge from neighbours of linked-entity into a medical PLM that integrates heterogeneous-entities into the homogeneously neighbouring entity structure.
Outcome:	Experiments show that SMedBERT outperforms baselines in knowledge-intensive Chinese medical tasks.

Copied to clipboard

Yihang Wang, Bin Wu, Yueyang Su, Tianfu Zhang, Yiqi Du, Lei Yu, Jiafeng Guo, Xueqi Cheng

Crossing Variational Autoencoders for Answer Retrieval (2020.acl-main)

Challenge:	Existing methods for quantizing large embeddings rely on Euclidean quantization, which is poorly aligned with the angular geometry induced by contrastive embeddment training.
Approach:	They propose a geometry-aware distillation method that compresses large embeddings into short discrete representations via iterative Householder transformations on the unit hypersphere.
Outcome:	The proposed method reduces decoding cost and maintains strong semantic retrieval accuracy.

Copied to clipboard

Wenhao Yu, Lingfei Wu, Qingkai Zeng, Shu Tao, Yu Deng, Meng Jiang

Introducing Graph Context into Language Models through Parameter-Efficient Fine-Tuning for Lexical Relation Mining (2025.acl-long)

Challenge:	Existing methods learned semantic representations with dual encoders or dual variational auto-encoders failed to capture the aligned semantics between question and answer.
Approach:	They propose to use two variational auto-encoders to generate questions with aligned answers and generating answers with align questions.
Outcome:	The proposed method outperforms the state-of-the-art answer retrieval method on SQuAD.

Copied to clipboard

Jingwen Sun, Zhiyi Tian, Yu He, Jingwei Sun, Guangzhong Sun

Scaling up Open Tagging from Tens to Thousands: Comprehension Empowered Attribute Value Extraction from Product Title (P19-1)

Challenge:	Pre-trained language models can effectively mine lexical relations between word pairs . however, graph features and semantic knowledge of pre-tried models are lacking in the task.
Approach:	They propose a parameter-efficient fine-tuning method which integrates graph features and semantic representations for lexical relation classification and lexic entailment tasks.
Outcome:	The proposed method integrates graph features and semantic representations for lexical relation mining tasks.

Copied to clipboard

Huimin Xu, Wenting Wang, Xin Mao, Xinyu Jiang, Man Lan

Aligning Images and Text with Semantic Role Labels for Fine-Grained Cross-Modal Understanding (2022.lrec-1)

Challenge:	Existing models treat each attribute as an entity type and build one set of NER tags for each of them, leading to scalability issues.
Approach:	They propose to regard attribute as a query and adopt only one global set of BIO tags for any attributes to reduce the burden of attribute tag or model explosion.
Outcome:	The proposed model outperforms state-of-the-art models and generates promising results for 8,906 attributes.

Copied to clipboard

Abhidip Bhattacharyya, Cecilia Mauceri, Martha Palmer, Christoffer Heckman

Multi-Granularity Interaction Network for Extractive and Abstractive Multi-Document Summarization (2020.acl-main)

Challenge:	Currently, image retrieval systems can retrieve relevant results for diverse inputs, but they do not provide a way to intentionally inject variety into the search results.
Approach:	They propose a multimodal dataset that combines semantic annotations with image bounding boxes.
Outcome:	The proposed system improves image retrieval performance and flexibility.

Copied to clipboard

Hanqi Jin, Tianming Wang, Xiaojun Wan

PCMID: Multi-Intent Detection through Supervised Prototypical Contrastive Learning (2023.findings-emnlp)

Challenge:	Existing methods for document summarization use extractive and abstractive representations, but they don't take into account hierarchical structure of document clusters.
Approach:	They propose a multi-granularity interaction network for extractive and abstractive multi-document summarization which jointly learn semantic representations for words, sentences, and documents.
Outcome:	The proposed model outperforms baseline methods and achieves the best results on the Multi-News dataset.

Copied to clipboard

Yurun Song, Junchen Zhao, Spencer Koehler, Amir Abdullah, Ian Harris

Introducing Semantics into Speech Encoders (2023.acl-long)

Challenge:	Existing approaches to intent detection assume that each utterance represents only a single intent.
Approach:	They propose a framework for intent detection that can learn multiple representations of a given user utterance under the context of different intent labels in an optimized semantic space.
Outcome:	The proposed framework achieves state-of-the-art on multiple public benchmark datasets and a private real-world dataset for the multi-intent detection task.

Copied to clipboard

Derek Xu, Shuyan Dong, Changhan Wang, Suyoun Kim, Zhaojiang Lin, Bing Liu, Akshat Shrivastava, Shang-Wen Li, Liang-Hsuan Tseng, Guan-Ting Lin, Alexei Baevski, Hung-yi Lee, Yizhou Sun, Wei Wang

Agentic Episodic Control (2026.findings-acl)

Challenge:	Existing self-supervised speech encoders contain primarily acoustic rather than semantic information.
Approach:	They propose a task-agnostic unsupervised way to incorporate semantic information from large language model (LLM) systems into self-supervised speech encoders without labeled audio transcriptions.
Outcome:	The proposed approach improves spoken language understanding (SLU) performance by over 5% on intent classification (IC), with modest gains in named entity resolution (NER) and slot filling (SF), and spoken question answering (SQA) score by over 22%.

Copied to clipboard

Xidong Yang, Wenhao Li, Junjie Sheng, Yun Hua, Haosheng Chen, Chuyun Shen, Xiangfeng Wang

Green & Sustainable NLP

Challenge:	Existing methods for reinforcement learning (RL) are limited by poor data efficiency and weak generalization.
Approach:	They propose a novel architecture that integrates large language models into episodic RL.
Outcome:	The proposed architecture achieves 2–6 higher data efficiency than baselines and is the only method to solve complex tasks like UnlockLocal with over 90% success.

Text Anomaly Detection with Simplified Isolation Kernel (2025.findings-emnlp)

Copied to clipboard

Yang Cao, Sikun Yang, Yujiu Yang, Lianyong Qi, Ming Liu

A Simple Contrastive Learning Framework for Interactive Argument Pair Identification via Argument-Context Extraction (2022.emnlp-main)

Challenge:	High-dimensional dense embeddings extracted by large language models pose memory requirements and high computation time.
Approach:	They propose a method that maps high-dimensional dense embeddings to lower-dimensional sparse representations while preserving crucial anomaly characteristics.
Outcome:	The proposed method achieves better detection performance than 11 SOTA anomaly detection algorithms while maintaining computational efficiency and low memory cost.

Copied to clipboard

Lida Shi, Fausto Giunchiglia, Rui Song, Daqian Shi, Tongtong Liu, Xiaolei Diao, Hao Xu

AudioStealer: Extracting Audio Prompts via Shapley Value-Guided Query Search (2026.findings-acl)

Challenge:	Existing work on argument mining uses context-based methods to identify whether two arguments are interactively related.
Approach:	They propose a contrastive learning framework to extract valuable information from the context.
Outcome:	The proposed framework achieves state-of-the-art performance on the benchmark dataset and visually displays more compact representations.

Copied to clipboard

Yingbin Jin, Xingjian Du, Hanjun Luo, Zihao Wang, Haibo Hu, XiaoFeng Wang, Xinfeng Li

Responsible & Trustworthy NLP

Challenge:	prompt stealing is a new form of attack that aims to reconstruct high-value prompts that guide music generation.
Approach:	They propose a method to steal music prompts from audio domains using a black-box attack framework.
Outcome:	The proposed method recovers prompts with high textual consistency to the ground truth while maintaining strong perceptual similarity to the target recordings.

Cross-Modal Taxonomic Generalization in (Vision-) Language Models (2026.acl-long)

Copied to clipboard

Tianyang Xu, Marcelo Sandoval-Castañeda, Karen Livescu, Greg Shakhnarovich, Kanishka Misra

Integrating Headedness Information into an Auto-generated Multilingual CCGbank for Improved Semantic Interpretation (2024.lrec-main)

Challenge:	Existing studies have shown that language models learn from surface form to learn from more grounded evidence.
Approach:	They propose to use a vision-language model to learn hypernyms from images . they find that the model can recover this knowledge and generalize even when there is no hypernomia in the image.
Outcome:	The proposed model can recover this knowledge and generalize even when the model receives no evidence of hypernyms during training.

Copied to clipboard

Tu-Anh Tran, Yusuke Miyao

Syntactic Text Processing

Challenge:	Combinatory Categorial Grammar is a grammar formalism that provides a transparent interface between syntax and semantics.
Approach:	They propose an algorithm that adds semantic representations to existing CCG derivations by combining them with predefined combinatory rules.
Outcome:	The proposed method produces bare CCG derivations without any accompanying semantic representations and limits its general applicability.

Joint Pre-Encoding Representation and Structure Embedding for Efficient and Low-Resource Knowledge Graph Completion (2024.emnlp-main)

Copied to clipboard

Chenyu Qiu, Pengjiang Qian, Chuang Wang, Jian Yao, Li Liu, Fang Wei, Eddie Eddie

Multi-Granularity Fusion Text Semantic Matching Based on WoBERT (2024.lrec-main)

Challenge:	Existing knowledge graph completion models require longer training and inference times as well as increased memory usage.
Approach:	They propose to encode textual descriptions into semantic representations before training and integrate structural embedding with pre-encoded semantic description to improve model's prediction performance on 1-N relations.
Outcome:	The proposed model increases inference speed by 30x and reduces training memory by approximately 60% on the WN18RR and UMLS datasets.

Copied to clipboard

Hongchun Yu, Wei Pan, Xing Fan, Hanqi Li

WhiSPA: Semantically and Psychologically Aligned Whisper with Self-Supervised Contrastive and Student-Teacher Learning (2025.acl-long)

Challenge:	Existing text-matching methods struggle with semantic nuances in short texts . a novel approach to improve text semantic matching is being developed .
Approach:	They propose a multi-granularity fusion model that harnesses a pre-trained language model to capture text semantic nuances.
Outcome:	The proposed model improves on Chinese short text matching datasets compared to traditional methods . the proposed model captures individual text semantic nuances and improves accuracy .

Copied to clipboard

Rajath Rao, Adithya V Ganesan, Oscar Kjell, Jonah Luby, Akshay Raghavan, Scott M. Feltman, Whitney Ringwald, Ryan L. Boyd, Benjamin J. Luft, Camilo J. Ruggero, Neville Ryant, Roman Kotov, H. Schwartz

Unveiling Multi-level and Multi-modal Semantic Representations in the Human Brain using Large Language Models (2024.emnlp-main)

Challenge:	Current speech encoding pipelines rely on an additional text-based LM to get robust representations of human communication, even though speech-to-text models often have a LM within.
Approach:	They propose to align Whisper's latent space with semantic representations from a text autoencoder and lexically derived embeddings of basic psychological dimensions: emotion and personality.
Outcome:	The proposed approach surpasses current speech encoders over self-supervised affective tasks and downstream psychological tasks, achieving an error reduction of 73.4% and 83.8%, respectively.

Copied to clipboard

Yuko Nakagi, Takuya Matsuyama, Naoko Koide-Majima, Hiroto Yamaguchi, Rieko Kubo, Shinji Nishimoto, Yu Takagi

ReCAP: Semantic Role Enhanced Caption Generation (2024.lrec-main)

Challenge:	Recent studies have assessed different levels of semantic content, such as speech, objects, and stories, separately.
Approach:	They used functional magnetic resonance imaging to record brain activity while watching 8.3 hours of dramas and movies.
Outcome:	The findings show that LLMs predict human brain activity more accurately than traditional language models, particularly for complex background stories.

Copied to clipboard

Abhidip Bhattacharyya, Martha Palmer, Christoffer Heckman

Reduce Redundancy Then Rerank: Enhancing Code Summarization with a Novel Pipeline Framework (2024.lrec-main)

Challenge:	Current vision language models lack specificity and overlook various aspects of the image.
Approach:	They propose to use semantic roles as control signals to guide captions to specific argument structures by focusing on specific objects and their associated semantic roles instead of general descriptions.
Outcome:	The proposed framework produces captions that exhibit enhanced quality, diversity, and controllability.

Copied to clipboard

Xiaoyu Hu, Xu Zhang, Zexu Lin, Deyu Zhou

Soft Well-Formed Semantic Parsing with Score-Based Selection (2024.lrec-main)

Challenge:	Existing code summarization models lack redundant tokens and are plagued by exposure bias.
Approach:	They propose a pipeline framework to reduce redundancy then rerank that eliminates redundant information in code representation space and a re-ranking model to select more suitable summary candidates.
Outcome:	The proposed framework overrides state-of-the-art approaches on six datasets from the CodeSearchNet benchmark.

Copied to clipboard

Jiangming Liu

Mitigating Hallucination in Large Vision-Language Models through Aligning Attention Distribution to Information Flow (2025.findings-emnlp)

Challenge:	Semantic parsing is the task of translating natural language into a structured, formal semantic representation that can be interpreted by machines.
Approach:	They propose a score-based method to select well-formed outputs from candidates generated by beam search algorithms.
Outcome:	The proposed method reduces the number of ill-formed outputs and improves F1 scores in English.

Copied to clipboard

Jianfei Zhao, Feng Zhang, Xin Sun, Chong Feng

How LLMs Comprehend Temporal Meaning in Narratives: A Case Study in Cognitive Evaluation of LLMs (2025.acl-long)

Challenge:	Decode-Only models propagate information from left to right, but the model's attention still focuses on the visual representations, resulting in hallucinations.
Approach:	They propose to leverage the core information embedded in semantic representations to enhance the model's visual understanding by leveraging the attention distributions.
Outcome:	The proposed method reduces hallucinations by 80% by aligning the attention distribution with the actual information flow.

Copied to clipboard

Karin De Langis, Jong Inn Park, Andreas Schramm, Bin Hu, Khanh Chi Le, Dongyeop Kang

Challenge:	Large language models exhibit increasingly sophisticated linguistic capabilities, yet the extent to which these models reflect human-like cognition versus advanced pattern recognition remains an open question.
Approach:	They conduct a series of targeted experiments to assess whether LLMs construct semantic representations and pragmatic inferences in a human-like manner.
Outcome:	The proposed framework can be used to assess the cognitive and linguistic capabilities of large language models (LLMs).

MAKI: Multi-layer Aligned Knowledge Injection for Structure-aware Knowledge Graph Completion with Large Language Models (2026.findings-acl)

Copied to clipboard

Zhiwen Xie, Xin Wang, Guangyou Zhou, Derek F. Wong

LLM-Guided Semantic Bootstrapping for Interpretable Text Classification with Tsetlin Machines (2026.findings-acl)

Challenge:	Existing knowledge graph completion methods struggle to capture structural information in knowledge graphs (KGs) Existing approaches for KGC focus on learning representations of entities and relations through observed structural patterns.
Approach:	They propose a multi-layer Aligned Knowledge Injection model that tightly integrates structured KG information into LLMs through multi-layered alignment.
Outcome:	The proposed method outperforms state-of-the-art methods on benchmark datasets.

Copied to clipboard

Jiechao Gao, Rohan Kumar Yadav, Yuangang Li, Yuandong Pan, Jie Wang, Ying Liu, Michael Lepech

Explainability & Interpretability in NLP

Challenge:	Pretrained language models (PLMs) provide strong semantic representations but are costly and opaque.
Approach:	They propose a framework that transfers pretrained language models into symbolic form and integrates them into symbolic models.
Outcome:	The proposed framework improves interpretability and accuracy across multiple text classification tasks while remaining fully symbolic and efficient.

Evaluating Perspectival Biases in Cross-Modal Retrieval (2026.findings-acl)

Copied to clipboard

Teerapol Saengsukhiran, Peerawat Chomphooyod, Narabodee Rodjananant, Chompakorn Chaksangchaichot, Patawee Prakrankamanant, Witthawin Sripheanpol, Pak Lovichit, Sarana Nutanong, Ekapol Chuangsuwanich

SemPA: Improving Sentence Embeddings of Large Language Models through Semantic Preference Alignment (2026.findings-acl)

Challenge:	a recent study shows that multimodal retrieval systems are expected to operate in a semantic space, agnostic to the language or cultural origin of the query.
Approach:	They introduce a benchmark to quantify linguistic and cultural biases in multimodal retrieval systems . they propose a framework to decouple language from culture and decouples it from semantics .
Outcome:	The proposed benchmark systematically measures the effects of linguistic and cultural biases on retrieval performance.

Copied to clipboard

Ziyang Chen, Zhenxuan Huang, Yile Wang, Weiqin Wang, Lu Yin, Hui Huang