TEXT REPRESENTATIONS

Infusing Finetuning with Semantic Dependencies (2021.tacl-1)

Challenge:	Existing methods for opinion summarization are limited due to the scarcity of data.
Approach:	They propose a system to perform unsupervised extractive opinion summarization using a dictionary-based representation learning model that generates topical representations of texts.
Outcome:	The proposed system achieves strong performance on three opinion summarization datasets.

Copied to clipboard

Zhaofeng Wu, Hao Peng, Noah A. Smith

It’s not Rocket Science: Interpreting Figurative Language in Narratives (2022.tacl-1)

Challenge:	Several diagnostics help to localize the benefits of our approach.
Approach:	They apply convolutional graph encoders to integrate semantic parses into task-specific finetuning.
Outcome:	The proposed approach yields benefits to natural language understanding (NLU) tasks in the GLUE benchmark.

Copied to clipboard

Tuhin Chakrabarty, Yejin Choi, Vered Shwartz

Sentiment Analysis

Challenge:	Existing text representations by design rely on compositionality, while figurative language is often non-compositional.
Approach:	They propose to use a pre-trained language model to interpret figurative language types to adopt human strategies for interpreting figurativ language types: inferring meaning from context and relying on constituent words’ literal meanings.
Outcome:	The proposed models perform significantly worse than humans on discriminative and generative tasks, bridging the gap from human performance.

Representing and Clustering Errors in Offensive Language Detection (2025.naacl-srw)

Copied to clipboard

Jood Otey, Laura Biester, Steven R Wilson

Deep Enhanced Representation for Implicit Discourse Relation Recognition (C18-1)

Challenge:	Sentence-BERT embeddings of Large Language Model (LLM)-generated linguistic features give the most interpretable clustering for Arabic errors.
Approach:	They evaluate the K-Means clustering of four text representations for the task of offensive language detection in English and Levantine Arabic.
Outcome:	The proposed clustering of four text representations for offensive language detection in English and Levantine Arabic gives the most human-interpretable clustering for English errors and the grouping is mainly based on the targeted group in the text.

Copied to clipboard

Hongxiao Bai, Hai Zhao

Pre-trained Semantic Interaction based Inductive Graph Neural Networks for Text Classification (2025.coling-main)

Challenge:	Discourse parsing requires understanding of text spans and can't be easily derived from surface features from sentence pairs.
Approach:	They propose a model augmented with different grained text representations to improve discourse relation recognition.
Outcome:	The proposed model achieves state-of-the-art accuracy with greater than 48% in 11-way and F1 score greater than 50% in 4-way classifications for the first time according to our best knowledge.

Copied to clipboard

Shiyu Wang, Gang Zhou, Jicang Lu, Jing Chen, Ningbo Huang

CitationIE: Leveraging the Citation Graph for Scientific Information Extraction (2021.acl-long)

Challenge:	Existing methods for text classification have vanishing or exploding gradients when dealing with long sequences, making it difficult to handle long-distance dependencies.
Approach:	They propose a graph neural network based on pre-trained semantic interaction called PaSIG . they construct a text-word heterogeneity graph and use context representation capability .
Outcome:	The proposed model outperforms existing methods on five datasets and achieves state-of-the-art performance.

Copied to clipboard

Vijay Viswanathan, Graham Neubig, Pengfei Liu

Fine-Tuning Large Language Models for Stock Return Prediction Using Newsflow (2024.emnlp-industry)

Challenge:	Existing work on scientific information extraction (SciIE) considers extraction solely based on the content of an individual paper, without considering the paper’s place in the broader literature.
Approach:	They propose to automate the extraction of key information from scientific documents by leveraging a complementary source: the citation graph of referential links between citing and cited papers.
Outcome:	The proposed model improves on a set of English-language scientific documents.

Copied to clipboard

Tian Guo, Emmanuel Hauptmann

On the Effect of Isotropy on VAE Representations of Text (2022.acl-short)

Challenge:	Quantitative investing relies on extracting quantitative features or signals from various data sources including market prices, economic indicators, financial text, etc.
Approach:	They propose to integrate LLMs’ token-level embeddings into a forecasting module and compare their results to those of encoder-only and decoder-based models.
Outcome:	The proposed model outperforms conventional sentiment scores on multiple investment universes and is based on encoder-only and decoder-based models.

Copied to clipboard

Lan Zhang, Wray Buntine, Ehsan Shareghi

Representation Learning

Challenge:	Injecting desired geometric properties into text representations has attracted a lot of attention due to its better utilisation of representation space.
Approach:	They propose to use an isotropic Gaussian posterior instead of the ellipsoidal Gausssian priori to inject isotropy into text representations.
Outcome:	The proposed method improves classification performance, robustness to input perturbation, and generative behavior compared to the ellipsoidal Gaussian posterior.

Cross-Lingual Representation Alignment Through Contrastive Image-Caption Tuning (2025.acl-short)

Copied to clipboard

Nathaniel Krasner, Nicholas Lanuzo, Antonios Anastasopoulos

Understanding Politics via Contextualized Discourse Processing (2021.emnlp-main)

Challenge:	Multilingual alignment of sentence representations has mostly required bitexts to bridge the gap between languages.
Approach:	They propose to use image captions to implicitly align text representations between languages to make them usable for cross-lingual Natural Language Understanding (NLU) and bitext retrieval.
Outcome:	The proposed approach is usable for cross-lingual Natural Language Understanding (NLU) and bitext retrieval.

Copied to clipboard

Rajkumar Pujari, Dan Goldwasser

Challenge:	Recent advances in pretrained language models do not capture nuanced biases in political discourse . a new approach to represent political content is to use contextualized embeddings to create effective representations .
Approach:	They propose a model that captures and leverages political content to generate more effective representations . they use tweets, press releases, issues, news articles and participating entities to generate composed representations.
Outcome:	The proposed model generates representations for political entities over multiple issues or events . qualitative and quantitative analysis shows that the model is meaningful and effective .

Is Anisotropy Truly Harmful? A Case Study on Text Clustering (2023.acl-short)

Copied to clipboard

Mira Ait-Saada, Mohamed Nadif

Text Clustering

Challenge:	Contextualized pre-trained representations are widely used as input to various tasks such as information retrieval, anomaly detection and document clustering.
Approach:	They propose to examine the impact of different transformations on isotropy and performance to assess the true impact of anisotropi.
Outcome:	The proposed model is based on a clustering task and shows that it has limited impact on expressiveness and closeness.

Improving Few-Shot Image Classification Using Machine- and User-Generated Natural Language Descriptions (2022.findings-naacl)

Copied to clipboard

Kosuke Nishida, Kyosuke Nishida, Shuichi Nishioka

Constructing contrastive samples via summarization for text classification with limited annotations (2021.findings-emnlp)

Challenge:	Humans can efficiently learn about new concepts from language descriptions, and we propose a new machine learning model, LIDE, which has a text decoder to generate the descriptions and a decoded text encoder to obtain the text representations of machine-generated descriptions.
Approach:	They propose a model with a text decoder to generate the descriptions and a corresponding text encoder to obtain the text representations of machine- or user-generated descriptions.
Outcome:	The proposed model outperforms baseline models with machine-generated descriptions and with high-quality user-generated models with high quality explanations.

Copied to clipboard

Yangkai Du, Tengfei Ma, Lingfei Wu, Fangli Xu, Xuhong Zhang, Bo Long, Shouling Ji

Language as a fingerprint: Self-supervised learning of user encodings using transformers (2022.findings-emnlp)

Challenge:	Various contrastive learning methods have been developed and lead to state-of-the-art performance in many computer vision tasks.
Approach:	They propose a method to construct efficient contrastive samples using text summarization to gain better representations of text classification tasks with limited annotations.
Outcome:	The proposed framework gains better representations on text classification tasks with limited annotations and is compared with existing methods on real-world text classification datasets.

Copied to clipboard

Roberta Rocca, Tal Yarkoni

Not Just Plain Text! Fuel Document-Level Relation Extraction with Explicit Syntax Refinement and Subsentence Modeling (2022.findings-emnlp)

Challenge:	Existing studies on individual differences and language representations focused on predicting selected attributes from text or conditioning text representations on author attributes.
Approach:	They propose a self-supervised approach to learning language-based user encodings using transformers.
Outcome:	The proposed model can pick up on complex linguistic signatures of users and infer rich information about them.

Copied to clipboard

Zhichao Duan, Xiuxing Li, Zhenyu Li, Zhuo Wang, Jianyong Wang

Enhancing Automated Essay Scoring Performance via Fine-tuning Pre-trained Language Models with Combination of Regression and Ranking (2020.findings-emnlp)

Challenge:	Document-level relation extraction (DocRE) aims to identify semantic labels among entities within a document.
Approach:	They propose a document-level relation extraction framework that captures and exploits instructive information by adding extra syntactic information into text representations.
Outcome:	The proposed framework outperforms existing methods on three benchmark datasets.

Copied to clipboard

Ruosong Yang, Jiannong Cao, Zhiyuan Wen, Youzheng Wu, Xiaodong He

Surveying the Dead Minds: Historical-Psychological Text Analysis with Contextualized Construct Representation (CCR) for Classical Chinese (2024.emnlp-main)

Challenge:	Recent work on sentence prediction tasks uses shallow neural networks to learn essay representations and constrain calculated scores with regression loss or ranking loss.
Approach:	They propose to use a pre-trained language model to learn text representations first and then to constrain the scores with regression loss or ranking loss.
Outcome:	The proposed model outperforms state-of-the-art models on the Automated Student Assessment Prize dataset.

Copied to clipboard

Yuqi Chen, Sixuan Li, Ying Li, Mohammad Atari

Robust Navigation with Language Pretraining and Stochastic Sampling (D19-1)

Challenge:	Humans have produced written language for thousands of years, but most computational work is focused on contemporary languages and corpora.
Approach:	They propose a pipeline for historical-psychological text analysis in classical Chinese . they propose an indirect contrastive learning approach that fine-tunes pre-trained models .
Outcome:	The proposed pipeline outperforms word-embedding-based approaches across all tasks and exceeds prompting with GPT-4 in most tasks.

Copied to clipboard

Xiujun Li, Chunyuan Li, Qiaolin Xia, Yonatan Bisk, Asli Celikyilmaz, Jianfeng Gao, Noah A. Smith, Yejin Choi

Robustness in NLP

Challenge:	Existing methods to learn visual representations and action decoding schemes are limited to previously unseen instructions and environments.
Approach:	They propose a stochastic sampling scheme to reduce the gap between the expert actions in training and sampled actions in test to correct its own mistakes.
Outcome:	The proposed methods achieve 6% absolute gain over the previous best results on the Room-to-Room benchmark.

Native Language Identification in Texts: A Survey (2024.naacl-long)

Copied to clipboard

Dhiman Goswami, Sharanya Thilagan, Kai North, Shervin Malmasi, Marcos Zampieri

Text Classification

Challenge:	Native language identification is the task of automatically identifying an author’s native language (L1) based on their second language production.
Approach:	They present a survey of native language identification applied to texts . authors describe several text representations and computational techniques used in the task .
Outcome:	The proposed task has been widely studied for both text and speech, particularly for L2 English due to the availability of suitable corpora.

Text-Guided Image Clustering (2024.eacl-long)

Copied to clipboard

Andreas Stephan, Lukas Miklautz, Kevin Sidak, Jan Philip Wahle, Bela Gipp, Claudia Plant, Benjamin Roth

Beyond End-to-End VLMs: Leveraging Intermediate Text Representations for Superior Flowchart Understanding (2025.naacl-long)

Challenge:	Current image clustering methods neglect the use of generated textual descriptions.
Approach:	They propose to use image captioning and visual question-answering to cluster images . they propose a new approach to inject task- or domain knowledge into image clustering .
Outcome:	The proposed method outperforms existing methods on eight image clustering datasets.

Copied to clipboard

Junyi Ye, Ankan Dash, Wenpeng Yin, Guiling Wang

Attending via both Fine-tuning and Compressing (2021.findings-acl)

Challenge:	Flowcharts are typically presented as images, driving the trend of using vision-language models for end-to-end flowchart understanding.
Approach:	They propose a vision-language model (VLM) that generates textual representations from flowchart images and a textual Reasoner that performs question-answering based on the text representations.
Outcome:	Experiments on the FlowVQA and FlowLearn benchmarks demonstrate TextFlow’s state-of-the-art performance as well as its robustness.

Copied to clipboard

Jie Zhou, Yuanbin Wu, Qin Chen, Xuanjing Huang, Liang He

Explainability & Interpretability in NLP

Challenge:	Existing studies show that attention mechanisms can improve models' interpretation, but they are not explicable.
Approach:	They propose a framework consisting of a learner and a compressor to purify attention scores . they propose to fine-tune and compress the attention mechanism to obtain a more faithful explanation .
Outcome:	The proposed framework improves performance and interpretability on eight benchmark datasets.

Do Large Language Models Mirror Cognitive Language Processing? (2025.coling-main)

Copied to clipboard

Yuqi Ren, Renren Jin, Tongxuan Zhang, Deyi Xiong

At the Intersection of NLP and Sustainable Development: Exploring the Impact of Demographic-Aware Text Representations in Modeling Value on a Corpus of Interviews (2022.lrec-1)

Challenge:	Large language models have demonstrated remarkable abilities in text comprehension and logical reasoning.
Approach:	They employ Representational Similarity Analysis to measure alignment between 23 LLMs and fMRI signals of the brain.
Outcome:	The results show that training strategies affect the LLM-brain alignment.

Copied to clipboard

Goya van Boven, Stephanie Hirmer, Costanza Conforti

Less is More: Pretrain a Strong Siamese Encoder for Dense Text Retrieval Using a Weak Decoder (2021.emnlp-main)

Challenge:	In order to preserve the privacy of speakers, we investigate encoding demographic information using autoencoders.
Approach:	They introduce a dataset of qualitative interviews from rural communities in India and Uganda and use it to enhance text representations with demographic information.
Outcome:	The proposed model extends the UPV classification model with demographic information to preserve the privacy of speakers.

Copied to clipboard

Shuqi Lu, Di He, Chenyan Xiong, Guolin Ke, Waleed Malik, Zhicheng Dou, Paul Bennett, Tie-Yan Liu, Arnold Overwijk

ITA: Image-Text Alignments for Multi-Modal Named Entity Recognition (2022.naacl-main)

Challenge:	Dense retrieval requires high-quality text sequence embeddings to support effective search in the representation space.
Approach:	They propose a self-learning method that pre-trains the autoencoder using a weak decoder to push the encoder to provide better sequence representations.
Outcome:	The proposed model significantly boosts the effectiveness and few-shot ability of dense retrieval models on web search, news recommendation, and open domain question answering.

Copied to clipboard

Xinyu Wang, Min Gui, Yong Jiang, Zixia Jia, Nguyen Bach, Tao Wang, Zhongqiang Huang, Kewei Tu

FactGraph: Evaluating Factuality in Summarization with Semantic Graph Representations (2022.naacl-main)

Challenge:	Recent work on Multi-modal Named Entity Recognition (MNER) relies on image information to model interactions between image and text representations.
Approach:	They propose to align image features into the textual space to better utilize attention mechanisms . they use regional object tags, captions and optical characters as visual contexts .
Outcome:	The proposed model can achieve state-of-the-art accuracy on multi-modal Named Entity Recognition datasets even without image information.

Copied to clipboard

Leonardo F. R. Ribeiro, Mengwen Liu, Iryna Gurevych, Markus Dreyer, Mohit Bansal

Attentive Pooling with Learnable Norms for Text Representation (2020.acl-main)

Challenge:	Recent studies show that abstractive summarization approaches generate summaries that are not factually consistent with the source document.
Approach:	They propose a method that decomposes the document and summary into structured meaning representations (MRs) MRs describe core semantic concepts and their relations, aggregating the main content in both document and summary in a canonical form .
Outcome:	The proposed method outperforms existing methods on benchmarks for factuality evaluation.

Copied to clipboard

Chuhan Wu, Fangzhao Wu, Tao Qi, Xiaohui Cui, Yongfeng Huang

Representation Learning

Challenge:	Existing pooling methods that use fixed pooling norms may not be optimal for learning text representations in different tasks.
Approach:	They propose to learn pooling norms in an end-to-end manner to automatically find the optimal ones for text representation in different tasks.
Outcome:	The proposed approach improves on four benchmark datasets on a neural NLP model.

Prompt-Singer: Controllable Singing-Voice-Synthesis with Natural Language Prompt (2024.naacl-long)

Copied to clipboard

Yongqi Wang, Ruofan Hu, Rongjie Huang, Zhiqing Hong, Ruiqi Li, Wenrui Liu, Fuming You, Tao Jin, Zhou Zhao

TreeMAN: Tree-enhanced Multimodal Attention Network for ICD Coding (2022.coling-1)

Challenge:	Recent singing-voice-synthesis methods lack ability to control style attributes of synthesized singing.
Approach:	They propose a singing-voice-synthesis method that enables attribute controlling on singer gender, vocal range and volume with natural language.
Outcome:	The proposed method achieves favorable control ability and audio quality.

Copied to clipboard

Zichen Liu, Xuyuan Liu, Yanlong Wen, Guoqing Zhao, Fen Xia, Xiaojie Yuan

Applying Automatic Text Summarization for Fake News Detection (2022.lrec-1)

Challenge:	Existing methods to automatically assign ICD codes ignore crucial information contained in structured medical data, which is hard to be captured from the noisy clinical notes.
Approach:	They propose to use a Tree-enhanced multimodal attention network to fuse tabular features and textual features into multimodal representations by enhancing the text representations with tree-based features.
Outcome:	The proposed method outperforms state-of-the-art methods on two MIMIC datasets.

Copied to clipboard

Philipp Hartl, Udo Kruschwitz

TAN-NTM: Topic Attention Networks for Neural Topic Modeling (2021.acl-long)

Challenge:	Social media has been a driver for the spread of misleading and deliberately wrong information, as there is little to no veracity monitoring.
Approach:	They propose a framework that combines transformer-based language models with contextual information to circumvent sequential limits and related loss of information.
Outcome:	The proposed framework can circumvent sequential limits and related loss of information on two publicly available datasets and achieve state-of-the-art performance benchmarks.

Copied to clipboard

Madhur Panwar, Shashank Shailabh, Milan Aggarwal, Balaji Krishnamurthy

Federated Learning for Spoken Language Understanding (2020.coling-main)

Challenge:	Topic models have been widely used to learn text representations and gain insight into document corpora.
Approach:	They propose a framework which processes document as a sequence of tokens through a LSTM whose contextual outputs are attended in a topic-aware manner.
Outcome:	The proposed model improves on two downstream tasks: document classification and topic guided keyphrase generation.

Copied to clipboard

Zhiqi Huang, Fenglin Liu, Yuexian Zou

Toeing the Party Line: Election Manifestos as a Key to Understand Political Discourse on Twitter (2024.findings-emnlp)

Challenge:	Existing methods to improve robustness of models focus on a single dataset . but, there are few studies on how to combine merits of different datasets .
Approach:	They propose a federated learning framework that could unify datasets and tasks . they propose MV-Encoder as backbone of the framework to provide multi-granularity text representations .
Outcome:	The proposed framework improves on two SLU benchmark datasets and federated learning settings.

Copied to clipboard

Maximilian Maurer, Tanise Ceron, Sebastian Padó, Gabriella Lapesa

Challenge:	Recent work on political positioning on Twitter has tended to focus on manifestos rather than social media since it is ambiguous and dependent on social context.
Approach:	They propose to use hashtags as a signal to fine-tune text representations for politicians' tweets using a hashtag-based method to predict pairwise positional similarities between parties from the manifesto case to the Twitter case.
Outcome:	The proposed method matches politicians' statements to official lines of the parties' tweets, even when only small subsets from shorter time periods are available.

Enhanced Language Representation with Label Knowledge for Span Extraction (2021.emnlp-main)

Copied to clipboard

Pan Yang, Xin Cong, Zhenyu Sun, Xingwu Liu

Representation Learning

Challenge:	Existing approaches to extract text spans from plain text do not fully exploit label knowledge.
Approach:	They propose a model to integrate label knowledge into text representations by encoding texts and annotations independently and then integrating label knowledge with an elaborate-designed semantics fusion module.
Outcome:	The proposed model achieves state-of-the-art performance on four benchmarks and reduces training time and inference time by 76% and 77% on average compared with the existing paradigm.

Offensive language detection in Hebrew: can other languages help? (2022.lrec-1)

Copied to clipboard

Marina Litvak, Natalia Vanetik, Chaya Liebeskind, Omar Hmdia, Rizek Abu Madeghem

Multilinguality

Challenge:	Various approaches for offensive language detection have been applied for this task . contamination of social networks with offensive content is a new reality affecting almost all of us .
Approach:	They propose to use multiple supervised models and text representations to detect offensive language in three languages, including two Semitic languages.
Outcome:	The proposed model can detect offensive content in two Semitic languages, including Hebrew and Arabic, and it is able to perform cross-lingual and multilingual learning.

Two-stage Generative Question Answering on Temporal Knowledge Graph Using Large Language Models (2024.findings-acl)

Copied to clipboard

Yifu Gao, Linbo Qiao, Zhigang Kan, Zhihua Wen, Yongquan He, Dongsheng Li

HiTIN: Hierarchy-aware Tree Isomorphism Network for Hierarchical Text Classification (2023.acl-long)

Challenge:	Temporal knowledge graph question answering (TKGQA) is one of the most challenging QA tasks due to the temporal constraints hidden in questions and the answers sought from dynamic structured knowledge.
Approach:	They propose a generative temporal knowledge graph question answering framework which guides LLMs to answer temporal questions through two phases: Subgraph Retrieval and Answer Generation.
Outcome:	The proposed framework exploits LLM’s intrinsic knowledge to mine temporal constraints and structural links in the questions without extra training, thus narrowing down the subgraph search space in both temporal and structural dimensions.

Copied to clipboard

He Zhu, Chong Zhang, Junjie Huang, Junran Wu, Ke Xu

On the Complementarity between Pre-Training and Random-Initialization for Resource-Rich Machine Translation (2022.coling-1)

Challenge:	Existing dual-encoder methods in HTC achieve weak performance gains with huge memory overheads and their structure encoders heavily rely on domain knowledge.
Approach:	They propose a hierarchy-aware tree isomorphism network to enhance the text representations with only syntactic information of the label hierarchy.
Outcome:	The proposed model could boost the performance of hierarchical text classification without prior statistics or label semantics without prior data.

Copied to clipboard

Changtong Zan, Liang Ding, Li Shen, Yu Cao, Weifeng Liu, Dacheng Tao

Multilinguality

Challenge:	Pre-Training (PT) of text representations has been successfully applied to low-resource Neural Machine Translation (NMT) however, it often fails to achieve notable gains on resource-rich NMT on par with its Random-Initialization (RI) counterpart.
Approach:	They propose to combine pre-training and random-initialization techniques to achieve significant improvements in NMT.
Outcome:	The proposed model fusion algorithm can achieve significant improvements on two resource-rich translation benchmarks.

Contextualized Graph Representations for Generating Counter-Narratives against Hate Speech (2024.findings-emnlp)

Copied to clipboard

Selene Baez Santamaria, Helena Gomez Adorno, Ilia Markov

Structured Data in NLP

Challenge:	Hate speech (HS) is a widespread problem in society with severe repercussions at both personal and societal levels.
Approach:	They propose to incorporate conversational history into CNs to confront biases and stereotypes driving hateful narratives.
Outcome:	The proposed strategies outperform existing methods on comparing graphical and text representations with varying degrees of context.

Empowering Backbone Models for Visual Text Generation with Input Granularity Control and Glyph-Aware Training (2024.emnlp-main)

Copied to clipboard

Wenbo Li, Guohao Li, Zhibin Lan, Xue Xu, Wanru Zhuang, Jiachen Liu, Xinyan Xiao, Jinsong Su

Visual Data in NLP

Challenge:	Existing text-to-image models struggle to generate images with legible visual texts . current models lack support for Chinese texts, misspelling, and lack of diversity .
Approach:	They propose to empower backbone models to generate visual texts in Chinese and English . they propose to augment conventional training objective with glyph-aware training losses .
Outcome:	The proposed methods can generate visual texts in English and Chinese while maintaining image generation quality.

Unsupervised Fine-tuning for Text Clustering (2020.coling-main)

Copied to clipboard

Shaohan Huang, Furu Wei, Lei Cui, Xingxing Zhang, Ming Zhou

Low-Resource NLP

Challenge:	Existing approaches to text clustering fine-tune pre-trained models have been limited.
Approach:	They propose a method to fine-tune pre-trained models unsupervisedly for text clustering by learning text representations and cluster assignments using a clustering oriented loss.
Outcome:	The proposed model outperforms baseline methods and achieves state-of-the-art results on three text clustering datasets.

Learning Easily Updated General Purpose Text Representations with Adaptable Task-Specific Prefix (2023.findings-emnlp)

Copied to clipboard

Kuan-Hao Huang, Liang Tan, Rui Hou, Sinong Wang, Amjad Almahairi, Ruty Rinott

Text Classification by Contrastive Learning and Cross-lingual Data Augmentation for Alzheimer’s Disease Detection (2020.coling-main)

Challenge:	a large pre-trained language model can cause computational burdens in inference time due to multiple forward passes.
Approach:	They propose a method to learn fixed text representations with source tasks . they learn a task-specific prefix for each source task independently and combine them .
Outcome:	The proposed method improves generalizability of representations with source tasks.

Copied to clipboard

Zhiqiang Guo, Zhaoci Liu, Zhenhua Ling, Shijin Wang, Lingjing Jin, Yunxia Li

Dual-Gated Fusion with Prefix-Tuning for Multi-Modal Relation Extraction (2023.findings-acl)

Challenge:	Existing methods for AD detection are too expensive and time-consuming to cover all potential patients.
Approach:	They propose a contrastive learning method to obtain effective text representations based on monolingual embeddings of BERT and a cross-lingual data augmentation method by building autoencoders to learn the text representation shared by both languages.
Outcome:	The proposed method outperforms other methods on a Mandarin AD corpus and achieves 81.6% detection accuracy.

Copied to clipboard

Qian Li, Shu Guo, Cheng Ji, Xutan Peng, Shiyao Cui, Jianxin Li, Lihong Wang

CAPE: Context-Aware Private Embeddings for Private Language Learning (2021.emnlp-main)

Challenge:	Existing methods for multi-modal relation extraction lack useful visual information.
Approach:	They propose a novel multi-modal relation extraction framework to capture deeper correlations of text, entity pair, and image/objects.
Outcome:	The proposed framework captures the deeper correlations of text, entity pair, and image/objects, and extracts useful information.

Copied to clipboard

Richard Plant, Dimitra Gkatzia, Valerio Giuffrida

Towards Better Representations for Multi-Label Text Classification with Multi-granularity Information (2023.findings-emnlp)

Challenge:	Existing methods to obtain text representations or embeddings with these models encoding personally identifiable information may lead to privacy leaks.
Approach:	They propose a novel approach which combines differential privacy and adversarial learning to preserve privacy during training of embeddings.
Outcome:	The proposed approach reduces private information leakage by 3% over the current method.

Copied to clipboard

Fangfang Li, Puzhen Su, Junwen Duan, Weidong Xiao

Deep Attention Diffusion Graph Neural Networks for Text Classification (2021.emnlp-main)

Challenge:	Existing studies have shown that pre-trained language models generate word frequency-oriented text representations, causing texts with different labels to be closely distributed in a narrow region, which is difficult to classify.
Approach:	They propose a framework to refine the text representation for multi-label text classification using contrastive learning and multi-task learning modules.
Outcome:	The proposed framework improves the quality of the representations and yields stable and competitive improvements.

Copied to clipboard

Yonghao Liu, Renchu Guan, Fausto Giunchiglia, Yanchun Liang, Xiaoyue Feng

An LLM-Enabled Knowledge Elicitation and Retrieval Framework for Zero-Shot Cross-Lingual Stance Identification (2024.findings-emnlp)

Challenge:	Existing methods for text classification based on graph neural networks (GNNs) consider only one-hop neighborhoods and low-frequency information within texts, which suffer from over-smoothing issues if many graph layers are stacked.
Approach:	They propose a deep attention diffusion Graph Neural Network model to learn text representations by bridging the chasm of interaction difficulties between a word and its distant neighbors.
Outcome:	The proposed model outperforms existing methods on standard benchmark datasets on a set of textual features.

Copied to clipboard

Ruike Zhang, Yuan Tian, Penghui Wei, Daniel Zeng, Wenji Mao

Low-Resource NLP

Challenge:	Existing research is conducted in monolingual setting on English datasets, whereas in other low-resource languages, it lacks sufficient data for training quality stance detection models.
Approach:	They propose a knowledge elicitation and retrieval framework that leverages the capability of large language models for stance knowledge acquisition and matches the target language input to the most relevant stance information.
Outcome:	The proposed framework improves on multilingual datasets and competitive baselines.

Boosting Event Extraction with Denoised Structure-to-Text Augmentation (2023.findings-acl)

Copied to clipboard

Bo Wang, Heyan Huang, Xiaochi Wei, Ge Shi, Xiao Liu, Chong Feng, Tong Zhou, Shuaiqiang Wang, Dawei Yin

Unsupervised Attention-based Sentence-Level Meta-Embeddings from Contextualised Language Models (2022.lrec-1)

Challenge:	Existing methods for event extraction neglect grammatical incorrectness, structure misalignment, and semantic drifting . et al., 2004; Ahn, 2006) show that the proposed method generates more diverse text representations for event extracting compared with the state-of-the-art.
Approach:	They propose a framework for event extraction that generates additional training data and iteratively selects the effective subset from the generated training data.
Outcome:	The proposed method generates more diverse representations of training data and achieves comparable results with the state-of-the-art.

Copied to clipboard

Keigo Takahashi, Danushka Bollegala

HapticCap: A Multimodal Dataset and Task for Understanding User Experience of Vibration Haptic Signals (2025.findings-emnlp)

Challenge:	Existing methods for creating metaembeddings from static word embeddings have been proposed, but they are not tied to a particular downstream task.
Approach:	They propose a sentence-level meta-embedding learning method that takes contextualised word embedding models and learns a phrase embeddable that preserves complementary strengths of the input source NLMs.
Outcome:	The proposed method outperforms existing methods on semantic textual similarity benchmarks on a supervised baseline and on token-level embeddings.

Copied to clipboard

Guimin Hu, Daniel Hershcovich, Hasti Seifi

Flipping Knowledge Distillation: Leveraging Small Models’ Expertise to Enhance LLMs in Text Matching (2025.acl-long)

Challenge:	a dataset of vibration haptic signals is developed to match descriptions to vibrations . a lack of large datasets annotated with textual descriptions is a challenge .
Approach:	They propose a multimodal dataset and task to match user descriptions to vibration haptic signals.
Outcome:	The proposed dataset matches user descriptions to vibration haptic signals . the results show that language models and audio models perform better than existing models .

Copied to clipboard

Mingzhe Li, Jing Xiang, Qishen Zhang, Kaiyang Wan, Xiuying Chen

On the Fragility of Active Learners for Text Classification (2024.emnlp-main)

Challenge:	Large Language Models (LLMs) have demonstrated remarkable capabilities in acquiring diverse knowledge, making them highly effective across a wide range of tasks.
Approach:	They propose a flipped knowledge distillation paradigm where LLM learns from SLM . they propose to reinterpret LLMs as encoder-decoder models using LoRA .
Outcome:	The proposed model has been deployed in an online application environment and validated on financial and healthcare benchmarks and real-world applications.

Copied to clipboard

Abhishek Ghose, Emma Nguyen