VECTOR REPRESENTATIONS

DialAug: Mixing up Dialogue Contexts in Contrastive Learning for Robust Conversational Modeling (2022.coling-1)

Challenge:	Existing retrieval methods rely on transforming user queries into vector representations and retrieving documents based on cosine similarity and static embeddings.
Approach:	They propose an inference-time logical reasoning framework that incorporates logical thinking into retrieval process.
Outcome:	The proposed method outperforms traditional retrieval methods on synthetic and real-world benchmarks on synthetic queries and datasets.

Copied to clipboard

Lahari Poddar, Peiyao Wang, Julia Reinspach

Post-Specialisation: Retrofitting Vectors of Words Unseen in Lexical Resources (N18-1)

Challenge:	a conversational system can learn to rank response candidates for a given dialogue context by computing similarity between their vector representations.
Approach:	They propose a framework that incorporates augmented dialogue contexts into the learning objective.
Outcome:	The proposed framework outperforms existing methods and is more robust to perturbations seen during inference.

Copied to clipboard

Ivan Vulić, Goran Glavaš, Nikola Mrkšić, Anna Korhonen

Evaluating Embedding APIs for Information Retrieval (2023.acl-industry)

Challenge:	Word vector specialisation is a portable, light-weight approach to fine-tuning distributional word vector spaces by injecting external knowledge from rich lexical resources such as WordNet.
Approach:	They propose a constraint-driven vector space specialisation method that embeds external knowledge into lexical resources into a deep neural network to specialise unseen words.
Outcome:	The proposed method preserves useful linguistic knowledge for seen words while propagating external signal to unseen words to improve their vector representations.

Copied to clipboard

Ehsan Kamalloo, Xinyu Zhang, Odunayo Ogundepo, Nandan Thakur, David Alfonso-hermelo, Mehdi Rezagholizadeh, Jimmy Lin

A Corpus to Learn Refer-to-as Relations for Nominals (L18-1)

Challenge:	a growing number of language models are limiting their access to the community . we evaluate existing APIs for domain generalization and multilingual retrieval .
Approach:	They evaluate semantic embedding APIs in retrieval scenarios to assess their capabilities . they use BEIR and MIRACL to re-rank BM25 results using the APIs .
Outcome:	The proposed model is based on semantic embedding APIs that build vector representations of a given text.

Copied to clipboard

Wasi Ahmad, Kai-Wei Chang

Reconstructing Event Regions for Event Extraction via Graph Attention Networks (2020.aacl-main)

Challenge:	Existing work on how to learn refer-to-as relations from large unlabeled corpora lacks coreferential information.
Approach:	They propose to use Wikipedia to generate coreferential neural embeddings for nominals . they use coreference resolution as a proxy to evaluate the neural embeds for noun phrases .
Outcome:	The proposed dataset can be leveraged to construct representations for coreferential nominals from Wikipedia.

Copied to clipboard

Pei Chen, Hang Yang, Kang Liu, Ruihong Huang, Yubo Chen, Taifeng Wang, Jun Zhao

Information Extraction & Text Mining

Challenge:	Existing approaches for event extraction focus on sentence-level event extraction, but they lack a broader view of the document context.
Approach:	They build graphs with candidate event filler extractions enriched by sentential embeddings as nodes and use graph attention networks to identify event regions in a document and aggregate event information.
Outcome:	The proposed method performs well on two languages and shows that it is faster than previous methods.

Improving Pretrained Models for Zero-shot Multi-label Text Classification through Reinforced Label Hierarchy Reasoning (2021.naacl-main)

Copied to clipboard

Hui Liu, Danqing Zhang, Bing Yin, Xiaodan Zhu

Language Models

Challenge:	Existing zero-shot learning methods for multi-label text classification mostly learn a matching model between the feature space of text and the label space.
Approach:	They propose to use a graph encoder to incorporate label hierarchies to learn effective label representations on the zero-shot multi-label text classification problem.
Outcome:	The proposed approach outperforms previous non-pretrained methods on the zero-shot multi-label text classification task.

MAR: Matching-Augmented Reasoning for Enhancing Visual-based Entity Question Answering (2024.emnlp-main)

Copied to clipboard

Zhengxuan Zhang, Yin Wu, Yuyu Luo, Nan Tang

Multimodality

Challenge:	Multimodal large language models (MLLMs) struggle with visual-based entity questions (VEQA) MLLM can identify A, but may refrain from answering due to privacy concerns.
Approach:	They propose a method that uses vector representations to analyze visual-based entity questions (VEQA) they use visual cues and textual information to integrate visual cus and visual information .
Outcome:	The proposed method significantly improves visual-based entity question answering (VEQA) it can identify faces, names, and alignments within visual objects, and then derive the answer over this matching graph.

Tsetlin Machine Embedding: Representing Words Using Logical Expressions (2024.findings-eacl)

Copied to clipboard

Bimal Bhattarai, Ole-Christoffer Granmo, Lei Jiao, Rohan Yadav, Jivitesh Sharma

Leveraging a Bilingual Dictionary to Learn Wolastoqey Word Representations (2022.lrec-1)

Challenge:	Embedding words in vector space is a fundamental first step in state-of-the-art natural language processing.
Approach:	They propose to embed words in vector space using propositional logic instead of dense vectors . they evaluate embeddings on intrinsic and extrinsic benchmarks and visualize word clusters based on their results .
Outcome:	The proposed model outperforms GLoVe on six classification tasks.

Copied to clipboard

Diego Bear, Paul Cook

Knowledge Graph Alignment with Entity-Pair Embedding (2020.emnlp-main)

Challenge:	Existing word embeddings for lowresource languages require large corpora of running text to learn high quality representations.
Approach:	They leverage a bilingual dictionary to learn Wolastoqey word embeddings by encoding their corresponding English definitions into vector representations using pretrained English word and sequence representation models.
Outcome:	The proposed model outperforms baseline models without language-specific training or fine-tuning.

Copied to clipboard

Zhichun Wang, Jinjian Yang, Xiaoju Ye

What Are You Token About? Dense Retrieval as Distributions Over the Vocabulary (2023.acl-long)

Challenge:	Existing methods for Knowledge Graph (KG) alignment are not satisfactory.
Approach:	They propose a method that directly learns embeddings of entity-pairs for KG alignment.
Outcome:	The proposed approach can achieve state-of-the-art on five real-world datasets.

Copied to clipboard

Ori Ram, Liat Bezalel, Adi Zicher, Yonatan Belinkov, Jonathan Berant, Amir Globerson

Multi-Granularity Contrasting for Cross-Lingual Pre-Training (2021.findings-acl)

Challenge:	Dense retrieval models based on text representations have proven very effective, but when applied off-the-shelf they often experience a severe drop in performance.
Approach:	They propose to interpret the vector representations produced by dual encoders by projecting them into the model’s vocabulary space.
Outcome:	The proposed model significantly improves on the BEIR benchmark and in zero-shot settings.

Copied to clipboard

Shicheng Li, Pengcheng Yang, Fuli Luo, Jun Xie

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

Challenge:	Existing approaches to pre-training focus on embedding alignment, but they neglect the modeling of bidirectional contexts.
Approach:	They propose a framework to learn languageuniversal representations using multi-granularity contrasting framework . they encode semantic equivalents from different languages into similar representations .
Outcome:	The proposed framework can achieve significant performance gains in machine translation and cross-lingual language understanding.

Copied to clipboard

Ignacio Iacobacci, Roberto Navigli

The Impact of Token Granularity on the Predictive Power of Language Model Surprisal (2025.acl-long)

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

Byung-Doh Oh, William Schuler

Language Models

Challenge:	Word-by-word language model surprisal is often used to model the incremental processing of human readers, but has been overlooked in cognitive modeling due to the granularity of subword tokens.
Approach:	They propose to manipulate token granularity to account for processing difficulty of naturalistic text and garden-path constructions.
Outcome:	The proposed model can account for the processing difficulty of naturalistic text and garden-path constructions by using tokens defined by a vocabulary size of 8,000.

Predicate-Conditional Conformalized Answer Sets for Knowledge Graph Embeddings (2025.findings-acl)

Copied to clipboard

Yuqicheng Zhu, Daniel Hernández, Yuan He, Zifeng Ding, Bo Xiong, Evgeny Kharlamov, Steffen Staab

Evaluation of Domain-specific Word Embeddings using Knowledge Resources (L18-1)

Challenge:	Existing methods provide probabilistic guarantees over a reference set of queries and answers, but they fail to identify when the answers to a query are uncertain.
Approach:	They propose a method that approximates predicate-conditional coverage guarantees while maintaining compact prediction sets.
Outcome:	The proposed method provides predicate-conditional coverage guarantees while maintaining compact prediction sets.

Copied to clipboard

Farhad Nooralahzadeh, Lilja Øvrelid, Jan Tore Lønning

Sequential Attention with Keyword Mask Model for Community-based Question Answering (N19-1)

Challenge:	Existing word embeddings capture a range of semantic relations relevant to the interpretation of lexical items, but domain-specific terms are difficult to evaluate because of a lack of statistical clues in the underlying corpus.
Approach:	They conduct intrinsic and extrinsic evaluations of both general and domain-specific embeddings and adapt embeddment enhancement methods to provide vector representations for infrequent and unseen terms.
Outcome:	The proposed model improves both in the intrinsic evaluation and extrinsic evaluation of the embedding models and their representations of infrequent and unseen terms.

Copied to clipboard

Jianxin Yang, Wenge Rong, Libin Shi, Zhang Xiong

Natural Language Interfaces

Challenge:	Existing methods to model answer selection(AS) are based on feature engineering and resource toolkits.
Approach:	They propose a model that captures features and information from question and answer text and repeats multiple times(hops) in a sequential fashion.
Outcome:	The proposed model performs on answer selection tasks and multi-level answer ranking tasks.

An Investigation of Potential Function Designs for Neural CRF (2020.findings-emnlp)

Copied to clipboard

Zechuan Hu, Yong Jiang, Nguyen Bach, Tao Wang, Zhongqiang Huang, Fei Huang, Kewei Tu

CDA: a Cost Efficient Content-based Multilingual Web Document Aligner (2021.eacl-main)

Challenge:	Existing approaches to sequence labeling are based on the neural linear-chain CRF model.
Approach:	They propose a series of increasingly expressive potential functions for neural CRF models that integrate emission and transition functions and explicitly take contextual words as input.
Outcome:	The proposed model consistently achieves the best performance on the decomposed quadrilinear potential function based on the representations of two neighboring labels and two neighbored words.

Copied to clipboard

Thuy Vu, Alessandro Moschitti

Simple Algorithms For Sentiment Analysis On Sentiment Rich, Data Poor Domains. (C18-1)

Challenge:	a Content-based document alignment approach is an efficient way to align multilingual web documents based on content.
Approach:	They propose a Content-based document alignment approach to align multilingual web documents based on content in parallel training data for machine translation systems.
Outcome:	The proposed method achieves comparable performance with state-of-the-art systems in the WMT-16 Bilingual Document Alignment Shared Task benchmark while operating in multilingual space.

Copied to clipboard

Prathusha K Sarma, William Sethares

On the Language Encoder of Contrastive Cross-modal Models (2024.findings-acl)

Challenge:	Standard word embedding algorithms learn vector representations from large corpora of text documents in unsupervised fashion.
Approach:	They propose an algorithm that learns word embeddings jointly with a classifier . their algorithm leverages document label information to learn vector representations of words .
Outcome:	The proposed algorithm has superior performance on domains with limited data compared to other methods.

Copied to clipboard

Mengjie Zhao, Junya Ono, Zhi Zhong, Chieh-Hsin Lai, Yuhta Takida, Naoki Murata, Wei-Hsiang Liao, Takashi Shibuya, Hiromi Wakaki, Yuki Mitsufuji

When Raw Data Prevails: Are Large Language Model Embeddings Effective in Numerical Data Representation for Medical Machine Learning Applications? (2024.findings-emnlp)

Challenge:	Pretrained audio-language models such as AudioCLIP and AudioCLAP have shown promising results on vision-language (VL) tasks.
Approach:	They extensively evaluate how unsupervised and supervised sentence embedding training affect language encoder quality and cross-modal task performance.
Outcome:	The proposed model improves on visual-language (VL) and audio-language tasks when the amount of training data is large.

Copied to clipboard

Yanjun Gao, Skatje Myers, Shan Chen, Dmitriy Dligach, Timothy Miller, Danielle Bitterman, Matthew Churpek, Majid Afshar

Certainty in Uncertainty: Reasoning over Uncertain Knowledge Graphs with Statistical Guarantees (2025.emnlp-main)

Challenge:	Numerical data is pivotal for medical questions and answers, but tabular data is not fully integrated into LLMs.
Approach:	They examine the effectiveness of vector representations from last hidden states of LLMs for medical diagnostics and prognostics using electronic health record data.
Outcome:	The proposed representations outperform those using raw numerical EHR data in medical diagnostics and prognostics.

Copied to clipboard

Yuqicheng Zhu, Jingcheng Wu, Yizhen Wang, Hongkuan Zhou, Jiaoyan Chen, Evgeny Kharlamov, Steffen Staab

Multimodality

Challenge:	Existing methods produce only point estimates, without quantifying predictive uncertainty—limiting their reliability in high-stakes applications where understanding confidence in predictions is crucial.
Approach:	They propose a framework that generates prediction intervals guaranteed to contain the true score with a user-specified level of confidence.
Outcome:	The proposed framework generates prediction intervals guaranteed to contain the true score with a user-specified level of confidence.

Context-aware Embedding for Targeted Aspect-based Sentiment Analysis (P19-1)

Copied to clipboard

Bin Liang, Jiachen Du, Ruifeng Xu, Binyang Li, Hejiao Huang

URIEL+: Enhancing Linguistic Inclusion and Usability in a Typological and Multilingual Knowledge Base (2025.coling-main)

Challenge:	Existing methods do not specifically pre-train reasonable embeddings for targets and aspects in TABSA.
Approach:	They propose to refine the embeddings of targets and aspects using a sparse coefficient vector . this allows the embeds to be refined from highly correlative words instead of context-independent vectors .
Outcome:	Experiments show that the proposed method improves on two benchmark datasets.

Copied to clipboard

Aditya Armaan Khan, Mason Stephen Shipton, David Anugraha, Kaiyao Duan, Phuong H. Hoang, Eric Khiu, A. Seza Doğruöz, Annie Lee

Multilinguality

Challenge:	URIEL is limited in terms of linguistic inclusion and overall usability . URIel+ provides robust, customizable distance calculations to better suit the needs of users.
Approach:	They propose a new version of URIEL and a query tool that provides a standardized approach to representing languages as geographical, phylogenetic, and typological vectors.
Outcome:	URIEL+ expands the user experience with robust, customizable distance calculations to better suit the needs of users.

xMoCo: Cross Momentum Contrastive Learning for Open-Domain Question Answering (2021.acl-long)

Copied to clipboard

Nan Yang, Furu Wei, Binxing Jiao, Daxing Jiang, Linjun Yang

A Semantic Feature-Wise Transformation Relation Network for Automatic Short Answer Grading (2021.emnlp-main)

Challenge:	Existing approaches to find relevant passages using sparse keywords are not effective for open domain question answering.
Approach:	They propose a new contrastive learning method for learning a dual-encoder model for question-passage matching using a large pool of negative samples.
Outcome:	The proposed method maintains large pool of negative samples and optimizes question-to-passage and passage-to question matching tasks.

Copied to clipboard

Zhaohui Li, Yajur Tomar, Rebecca J. Passonneau

Challenge:	Multiple choice questions can be graded automatically, but automated short answer grading is time-consuming and has bias and errors.
Approach:	They propose a Semantic Feature-wise transformation Relation Network that captures relational knowledge among the questions, reference answers or rubrics and labeled student answers.
Outcome:	The proposed model has up to 11% performance improvement over state-of-the-art approaches on the benchmark SemEval-2013 datasets, and surpasses custom approaches designed for a Kaggle challenge.

Combining rule-based and embedding-based approaches to normalize textual entities with an ontology (L18-1)

Copied to clipboard

Arnaud Ferré, Louise Deléger, Pierre Zweigenbaum, Claire Nédellec

Multi-word Measures: Modeling Semantic Change in Compound Nouns (2025.findings-acl)

Challenge:	a method to normalize multi-word terms with concepts from a domain-specific ontology is proposed . a large part of knowledge is expressed in textual form, such as in scientific articles .
Approach:	They propose a method to normalize multi-word terms with concepts from a domain-specific ontology.
Outcome:	The proposed method outperforms existing methods on a categorization task in bacterial habitats . the results are encouraging, and the proposed method is expected to be widely used in the biomedical/biological field .

Copied to clipboard

Chris Jenkins, Filip Miletić, Sabine Schulte Im Walde

Text Clustering

Challenge:	Compound words provide a multifaceted challenge for diachronic models of semantic change . novel sense-targeting approach targets both noun compounds and their constituent parts .
Approach:	They propose a dataset of relatedness judgements of noun compounds in English and german . they use contrasting vector representations to evaluate their ability to cluster example sentence pairs .
Outcome:	The proposed approach captures diachronic meaning changes for multi-word expressions without condensing individual senses into an aggregate value.

LightRAG: Simple and Fast Retrieval-Augmented Generation (2025.findings-emnlp)

Copied to clipboard

Zirui Guo, Lianghao Xia, Yanhua Yu, Tu Ao, Chao Huang

Green & Sustainable NLP

Challenge:	Existing RAG systems rely on flat data representations and inadequate contextual awareness . lightRAG framework incorporates graph structures into text indexing and retrieval processes .
Approach:	LightRAG is a framework that integrates graph structures into text indexing and retrieval processes.
Outcome:	The proposed framework incorporates graph structures into text indexing and retrieval processes.

Multilingual Grammar Induction with Continuous Language Identification (D19-1)

Copied to clipboard

Wenjuan Han, Ge Wang, Yong Jiang, Kewei Tu

Information Retrieval

Challenge:	Existing methods to induce grammars of multiple languages do not consider language similarity measures.
Approach:	They propose a universal grammar induction approach that captures similarity between languages . they use vector representations to capture similarity and softly tie grammar parameters .
Outcome:	The proposed approach performs well over monolingual and multilingual datasets.

Embedding Lexical Features via Tensor Decomposition for Small Sample Humor Recognition (D19-1)

Copied to clipboard

Zhenjie Zhao, Andrew Cattle, Evangelos Papalexakis, Xiaojuan Ma

A Simple Geometric Method for Cross-Lingual Linguistic Transformations with Pre-trained Autoencoders (2021.emnlp-main)

Challenge:	Existing methods for humor recognition require a large amount of training data with labels to learn effective features.
Approach:	They propose a tensor embedding method that can extract lexical humor features for continuous humor recognition by using word-word co-occurrence to encode contextual content of documents, and then decompose the tenor to get corresponding vector representations.
Outcome:	The proposed method achieves a distance of 0.887 on a global humor ranking task, comparable to the top performing systems from SemEval 2017 Task 6B, but without the need for any external training corpus.

Copied to clipboard

Maarten De Raedt, Fréderic Godin, Pieter Buteneers, Chris Develder, Thomas Demeester

Quantifying Character Similarity with Vision Transformers (2023.emnlp-main)

Challenge:	Existing studies have used probing tasks to verify the presence of linguistic properties in vector representations, but it is unclear whether they can be manipulated to indirectly steer them.
Approach:	They validate a geometric mapping technique to transform linguistic properties without tuning . they use a pre-trained multilingual autoencoder to transform three linguistic property .
Outcome:	The proposed method can be used without tuning of the pre-trained autoencoder . the results are validated in monolingual and cross-lingual settings .

Copied to clipboard

Xinmei Yang, Abhishek Arora, Shao-Yu Jheng, Melissa Dell

Multimodality

Challenge:	Off-the-shelf string matching methods are widely used to link entities across datasets, but they are not available for many settings.
Approach:	They propose to use augmented digital fonts to measure character substitution costs for OCR’ed documents by using vision transformers.
Outcome:	The proposed method significantly improves record linkage compared to other string matching methods.

Sentence Embedding Leaks More Information than You Expect: Generative Embedding Inversion Attack to Recover the Whole Sentence (2023.findings-acl)

Copied to clipboard

Haoran Li, Mingshi Xu, Yangqiu Song

Context or Knowledge is Not Always Necessary: A Contrastive Learning Framework for Emotion Recognition in Conversations (2023.findings-acl)

Challenge:	Sentence-level representations are beneficial for various natural language processing tasks.
Approach:	They propose a generative embedding inversion attack that reconstructs input sequences based only on their sentence embeddeds.
Outcome:	The proposed model outperforms previous embedding inversion attacks in classification metrics and generates coherent and contextually similar sentences as original inputs.

Copied to clipboard

Geng Tu, Bin Liang, Ruibin Mao, Min Yang, Ruifeng Xu

Bridging Continuous and Discrete Spaces: Interpretable Sentence Representation Learning via Compositional Operations (2023.emnlp-main)

Challenge:	Existing studies focus on modeling context-sensitive dependencies and knowledge-sensitive dependences.
Approach:	They propose a framework based on contrastive learning called CKCL to distinguish utterances for better vector representations.
Outcome:	The proposed framework outperforms state-of-the-art models on four datasets.

Copied to clipboard

James Y. Huang, Wenlin Yao, Kaiqiang Song, Hongming Zhang, Muhao Chen, Dong Yu

Does Visual Grounding Enhance the Understanding of Embodied Knowledge in Large Language Models? (2025.findings-emnlp)

Challenge:	Existing approaches to learn sentence embeddings do not capture the semantic similarity of sentences.
Approach:	They propose a framework that integrates compositional sentence operations into the embedding space and optimizes operator networks and a bottleneck encoder-decoder model to produce meaningful and interpretable sentence embeddables.
Outcome:	The proposed framework improves the interpretability of sentence embeddings on four textual generation tasks while maintaining strong performance on traditional semantic similarity tasks.

Copied to clipboard

Zhihui Yang, Yupei Wang, Kaijie Mo, Zhe Zhao, Renfen Hu

What’s in a prompt? Language models encode literary style in prompt embeddings (2025.emnlp-main)

Challenge:	Despite significant progress in multimodal language models, it remains unclear whether visual grounding enhances their understanding of embodied knowledge compared to text-only models.
Approach:	They propose to assess vision-language models’ perceptual abilities across different sensory modalities through vector comparison and question-answering tasks with over 1,700 questions.
Outcome:	The proposed benchmark assesses the models’ perceptual abilities across different sensory modalities through vector comparison and question-answering tasks with over 1,700 questions.

Copied to clipboard

Raphaël Sarfati, Haley Moller, Toni J.b. Liu, Nicolas Boulle, Christopher Earls

PRISM: A Framework for Producing Interpretable Political Bias Embeddings with Political-Aware Cross-Encoder (2025.acl-long)

Challenge:	Large language models encode textual information using high-dimensional latent spaces . many studies have investigated how conceptual content of words translates into geometrical relationships between their vector representations .
Approach:	They use literary pieces to show that intangible, rather than factual, aspects of the prompt are contained in deep representations.
Outcome:	The results show that word-to-vec(tor) embeddings are more complex than other models.

Copied to clipboard

Yiqun Sun, Qiang Huang, Anthony Kum Hoe Tung, Jun Yu