RELATION CLASSIFICATION

Multimodal Fallacy Classification in Political Debates (2024.eacl-short)

Challenge:	Existing supervised systems are highly data-driven and require a lot of effort to label data for a new domain.
Approach:	They propose to transfer knowledge from one or more related source domains to another domain to improve relation classification.
Outcome:	The proposed model outperforms neural-network based models on biomedical datasets and with contextualized embeddings on 3 biomedically-relevant datasets.

Copied to clipboard

Eleonora Mancini, Federico Ruggeri, Paolo Torroni

Text Classification

Challenge:	Recent advances in NLP suggest that some tasks, such as argument detection and relation classification, are better framed in a multimodal perspective.
Approach:	They propose to use multimodal argument mining to capture paralinguistic aspects of fallacious arguments.
Outcome:	The proposed multimodal argument mining improves argument detection and relation classification in political debates.

UniRE: A Unified Label Space for Entity Relation Extraction (2021.acl-long)

Copied to clipboard

Yijun Wang, Changzhi Sun, Yuanbin Wu, Hao Zhou, Lei Li, Junchi Yan

TTM-RE: Memory-Augmented Document-Level Relation Extraction (2024.acl-long)

Challenge:	Existing joint entity relation extraction models setup two separate label spaces for the two sub-tasks .
Approach:	They propose to eliminate the different treatment on the two sub-tasks’ label spaces by applying a unified classifier to predict each cell’s label.
Outcome:	The proposed model achieves competitive accuracy with the best extractor and is faster.

Copied to clipboard

Chufan Gao, Xuan Wang, Jimeng Sun

The RELX Dataset and Matching the Multilingual Blanks for Cross-Lingual Relation Classification (2020.findings-emnlp)

Challenge:	Existing methods for document-level relation extraction are ineffective in exploiting the full potential of large amounts of training data with varied noise levels.
Approach:	They propose a novel approach that integrates a trainable memory module with a noisy-robust loss function that accounts for the positive-unlabeled setting to unlock the full potential of large-scale noisy training data.
Outcome:	The proposed model outperforms existing methods on a ReDocRED benchmark dataset with an absolute F1 score improvement of over 3%.

Copied to clipboard

Abdullatif Köksal, Arzucan Özgür

Relation Classification with Entity Type Restriction (2021.findings-acl)

Challenge:	Current approaches for relation classification are focused on the English language and require lots of training data with human annotations.
Approach:	They propose a baseline model based on Multilingual BERT and a new multilingual pretraining setup . they propose 'relationship classification' models that use distant supervision .
Outcome:	The proposed model significantly improves the baseline model with distant supervision.

Copied to clipboard

Shengfei Lyu, Huanhuan Chen

Revisiting Few-shot Relation Classification: Evaluation Data and Classification Schemes (2021.tacl-1)

Challenge:	Existing methods regard all relations as candidate relations for the two entities, which leads to inappropriate relations being candidate relations.
Approach:	They propose a paradigm which exploits entity types to restrict candidate relations by mutual restrictions.
Outcome:	The proposed paradigm improves GCN and SpanBERT on a standard dataset by 6.9 and 4.4 F1 points.

Copied to clipboard

Ofer Sabo, Yanai Elazar, Yoav Goldberg, Ido Dagan

DSGAN: Generative Adversarial Training for Distant Supervision Relation Extraction (P18-1)

Challenge:	a recent study has focused on few-shot learning (FSL) for relation classification, but it requires large amounts of training data.
Approach:	They propose a method for deriving more realistic few-shot test data from available datasets for supervised RC.
Outcome:	The proposed method yields a challenging benchmark for FSL-RC on which state of the art models show poor performance.

Copied to clipboard

Pengda Qin, Weiran Xu, William Yang Wang

Efficient Information Extraction in Few-Shot Relation Classification through Contrastive Representation Learning (2024.naacl-short)

Challenge:	Distant supervision can effectively label data for relation extraction, but suffers from the noise labeling problem.
Approach:	They propose a sentence-level true-positive generator to learn a true-negative generator from a fuzzy sentence bag.
Outcome:	The proposed method significantly improves the performance of distant supervision relation extraction compared to state-of-the-art systems.

Copied to clipboard

Philipp Borchert, Jochen De Weerdt, Marie-Francine Moens

Responsible & Trustworthy NLP

Challenge:	Relation classification (RC) models extract rich information from sentences with limited labeled instances.
Approach:	They propose to combine multiple sentence representations with contrastive learning to enhance information extraction by combining multiple sentence and entity tokens.
Outcome:	The proposed approach is able to extract discriminative information from multiple representations and contrastive learning.

Structure Regularized Neural Network for Entity Relation Classification for Chinese Literature Text (N18-2)

Copied to clipboard

Ji Wen, Xu Sun, Xuancheng Ren, Qi Su

Frowning Frodo, Wincing Leia, and a Seriously Great Friendship: Learning to Classify Emotional Relationships of Fictional Characters (N19-1)

Challenge:	Existing methods for relation classification have been used in natural language processing.
Approach:	They propose a relation classification task for Chinese literature text using a new dataset.
Outcome:	The proposed model outperforms the state-of-the-art methods on Chinese literature text.

Copied to clipboard

Evgeny Kim, Roman Klinger

DeepStruct: Pretraining of Language Models for Structure Prediction (2022.findings-acl)

Challenge:	Existing literature analysis does not focus on roles of characters or on relationships between them.
Approach:	They propose to combine emotion and character identification into a unified framework for character network extraction from fictional texts.
Outcome:	The proposed task is based on fan-fiction short stories and is able to predict emotion relations in the extracted network graph.

Copied to clipboard

Chenguang Wang, Xiao Liu, Zui Chen, Haoyun Hong, Jie Tang, Dawn Song

Zero-Shot Information Extraction as a Unified Text-to-Triple Translation (2021.emnlp-main)

Challenge:	Pretrained language models perform structural understanding tasks that focus on understanding one aspect of the text.
Approach:	They propose a method for improving the structural understanding abilities of language models by pretraining them to generate structures from the text on task-agnostic corpora.
Outcome:	The proposed model performs state-of-the-art on 21 of 28 datasets.

Copied to clipboard

Chenguang Wang, Xiao Liu, Zui Chen, Haoyun Hong, Jie Tang, Dawn Song

Neural Relation Classification with Text Descriptions (C18-1)

Challenge:	a number of information extraction tasks require task-specific training.
Approach:	They propose a text-to-triple translation framework for information extraction tasks . they propose enabling task-agnostic translation by leveraging latent knowledge of a pre-trained language model .
Outcome:	The proposed framework outperforms the existing methods on open information extraction tasks.

Copied to clipboard

Feiliang Ren, Di Zhou, Zhihui Liu, Yongcheng Li, Rongsheng Zhao, Yongkang Liu, Xiaobo Liang

Incremental Few-shot Text Classification with Multi-round New Classes: Formulation, Dataset and System (2021.naacl-main)

Challenge:	State-of-the-art methods for relation classification suffer from data sparsity issue greatly.
Approach:	They propose a new neural relation classification method which integrates entities’ text descriptions into deep neural networks models.
Outcome:	The proposed method achieves much better experimental results than other state-of-the-art methods on the SemEval 2010 dataset.

Copied to clipboard

Congying Xia, Wenpeng Yin, Yihao Feng, Philip Yu

Low-Resource NLP

Challenge:	Text classification is usually studied by labeling texts with relevant categories from a predefined set.
Approach:	They propose a task where a system incrementally handles multiple rounds of new classes . they propose two entailment approaches, ENTAILMENT and HYBRID, which show promise .
Outcome:	The proposed task is based on a few-shot text classification task in the NLP domain.

Relation-Specific Attentions over Entity Mentions for Enhanced Document-Level Relation Extraction (2022.naacl-main)

Copied to clipboard

Jiaxin Yu, Deqing Yang, Shuyu Tian

K-Adapter: Infusing Knowledge into Pre-Trained Models with Adapters (2021.findings-acl)

Challenge:	Existing document-level relation extraction methods do not distinguish between mention-level features and entity-level feature . document-based methods are more challenging because of multiple mentions of entities.
Approach:	They propose a method which selectively attentions different entity mentions with respect to candidate relations and performs relation-specific representations of entities.
Outcome:	The proposed method improves relation-specific representations of entities on two benchmark datasets.

Copied to clipboard

Ruize Wang, Duyu Tang, Nan Duan, Zhongyu Wei, Xuanjing Huang, Jianshu Ji, Guihong Cao, Daxin Jiang, Ming Zhou

Argument Mining as a Text-to-Text Generation Task (2024.eacl-long)

Challenge:	Existing methods for injecting knowledge into pre-trained models are inconsistent and can flush out knowledge when multiple kinds of knowledge are injected.
Approach:	They propose a framework that retains the original parameters of pre-trained models fixed and supports the development of versatile knowledge-infused models.
Outcome:	The proposed framework retains the original parameters of the pre-trained model fixed and supports the development of versatile knowledge-infused models.

Copied to clipboard

Masayuki Kawarada, Tsutomu Hirao, Wataru Uchida, Masaaki Nagata

Text Generation

Challenge:	Argument Mining (AM) aims to uncover the argumentative structures within a text.
Approach:	They propose a method that generates argumentatively annotated text using a pretrained encoder-decoder language model and a pre-trained decoder.
Outcome:	The proposed method achieves state-of-the-art performance on three types of benchmark datasets.

Exploiting Entity BIO Tag Embeddings and Multi-task Learning for Relation Extraction with Imbalanced Data (P19-1)

Copied to clipboard

Wei Ye, Bo Li, Rui Xie, Zhonghao Sheng, Long Chen, Shikun Zhang

Fine-tuning Pre-Trained Transformer Language Models to Distantly Supervised Relation Extraction (P19-1)

Challenge:	Existing methods to perform relation extraction are feature-based or kernel-based, but the results of our study show that they can improve the performance of a baseline model with more than 10% absolute increase in F1-score.
Approach:	They propose a multi-task architecture which jointly trains a model to perform relation identification with cross-entropy loss and relation classification with ranking loss.
Outcome:	The proposed model outperforms the state-of-the-art models on ACE 2005 Chinese and English corpus and significantly improves the performance of a baseline model with more than 10% increase in F1-score.

Copied to clipboard

Christoph Alt, Marc Hübner, Leonhard Hennig

ARNOR: Attention Regularization based Noise Reduction for Distant Supervision Relation Classification (P19-1)

Challenge:	Current relation extraction methods suffer from noisy labels and incomplete knowledge base information.
Approach:	They propose a pre-trained language model that captures semantic and syntactic features and a significant amount of “common-sense” knowledge.
Outcome:	The proposed model achieves state-of-the-art AUC score of 0.422 on the NYT10 dataset and performs especially well at higher recall levels.

Copied to clipboard

Wei Jia, Dai Dai, Xinyan Xiao, Hua Wu

Explainability & Interpretability in NLP

Challenge:	Distant supervision is used for relation classification but it introduces noisy labels . a novel approach to distant supervision relation classification is proposed .
Approach:	They propose a framework for distant supervision relation classification using attention regularization and attention regularizing . they assume that a trustable relation label should be explained by the neural attention model .
Outcome:	The proposed framework improves on the NYT data and noise reduction effect over state-of-the-art methods.

MIMIC: Multi-party Dialogue Augmentation via Speaker Stylistic Transfer (2026.findings-eacl)

Copied to clipboard

Gaetano Cimino, Giuseppe Carenini, Vincenzo Deufemia

Dialogue Systems & Conversational Agents

Challenge:	Existing discourse annotations are limited and annotated data scarcity has hindered progress in discourse parsing.
Approach:	They propose a framework for augmenting discourse-annotated corpora via speaker stylistic transfer using Large Language Models (LLMs).
Outcome:	The proposed framework outperforms parsers trained on STAC and Molweni corpora on a multi-party dialogue with consistent gains for underrepresented discourse patterns and in low-resource scenarios.

Logical Form Generation via Multi-task Learning for Complex Question Answering over Knowledge Bases (2022.coling-1)

Copied to clipboard

Xixin Hu, Xuan Wu, Yiheng Shu, Yuzhong Qu

ICA-Proto: Iterative Cross Alignment Prototypical Network for Incremental Few-Shot Relation Classification (2023.findings-eacl)

Challenge:	Existing generation-based KBQA methods that translate natural language questions to executable logical forms are proving promising but noise introduced can lead to incorrect results.
Approach:	They propose a Generation-based KBQA method that uses auxiliary information to enhance logical form generation by combining unseen KB items with novel combinations.
Outcome:	The proposed method achieves state-of-the-art results on ComplexWebQuestions and WebQuestIONSSP datasets.

Copied to clipboard

Wangjie Jiang, Zhihao Ye, Bang Liu, Ruihui Zhao, Jianguang Zheng, Mengyao Li, Zhiyong Li, Yujiu Yang, Yefeng Zheng

Unified Semantic Typing with Meaningful Label Inference (2022.naacl-main)

Challenge:	Existing methods for relation classification suffer from the scarcity of manually annotated data.
Approach:	They propose a novel relation classification model that incorporates query representation into the encoding of novel prototypes and utilizes iteratively to achieve more interaction.
Outcome:	The proposed model outperforms the state-of-the-art model on two benchmark datasets.

Copied to clipboard

James Y. Huang, Bangzheng Li, Jiashu Xu, Muhao Chen

Exploratory Neural Relation Classification for Domain Knowledge Acquisition (C18-1)

Challenge:	Semantic typing aims at classifying tokens into semantic categories such as relations, entity types, and event types.
Approach:	They propose a unified framework for semantic typing that captures label semantics by projecting both inputs and labels into a joint semantic embedding space.
Outcome:	The proposed framework achieves strong performance across three semantic typing tasks.

Copied to clipboard

Yan Fan, Chengyu Wang, Xiaofeng He

MatSci-NLP: Evaluating Scientific Language Models on Materials Science Language Tasks Using Text-to-Schema Modeling (2023.acl-long)

Challenge:	Existing methods for relation classification are limited and lack of low-frequency relations in specific domains.
Approach:	They propose a method to learn a classifier on pre-defined relations and discover new relations expressed in texts.
Outcome:	The proposed method can classify entities into a finite set of relations and discover relations with high precision and recall.

Copied to clipboard

Yu Song, Santiago Miret, Bang Liu

Large-scale Exploration of Neural Relation Classification Architectures (D18-1)

Challenge:	Using publicly available materials science text data, we construct a benchmark for evaluating the performance of natural language processing (NLP) models on materials science texts.
Approach:	They propose a natural language benchmark for evaluating the performance of natural language processing (NLP) models on materials science text.
Outcome:	The proposed model outperforms BERT-based models on scientific text and a model pretrained on materials science journals.

Copied to clipboard

Hoang-Quynh Le, Duy-Cat Can, Sinh T. Vu, Thanh Hai Dang, Mohammad Taher Pilehvar, Nigel Collier

Text Classification

Challenge:	Existing studies on relation classification have been limited to a very narrow range of datasets, making comparisons between approaches difficult.
Approach:	They propose a multi-channel LSTM model combined with a CNN that takes advantage of all currently popular linguistic and architectural features.
Outcome:	The proposed model achieves state-of-the-art on two datasets and provides direct insights into the challenges faced by language models on relation classification.

CrossRE: A Cross-Domain Dataset for Relation Extraction (2022.findings-emnlp)

Copied to clipboard

Elisa Bassignana, Barbara Plank

Relation Classification Using Segment-Level Attention-based CNN and Dependency-based RNN (N19-1)

Challenge:	Relation Extraction (RE) evaluation is limited to in-domain setups . despite the drought of research on cross-domain RE, its practical importance remains .
Approach:	They propose a cross-domain benchmark for relation extraction which includes multi-label annotations and meta-data to include explanations and flags of difficult instances.
Outcome:	The proposed model includes explanations and flags of difficult instances.

Copied to clipboard

Van-Hien Tran, Van-Thuy Phi, Hiroyuki Shindo, Yuji Matsumoto

SelfORE: Self-supervised Relational Feature Learning for Open Relation Extraction (2020.emnlp-main)

Challenge:	Recent work on relation classification has gained much success by exploiting deep neural networks.
Approach:	They propose a relation classification model using Segment-level Attention-based Convolutional Neural Networks and Dependency-based Recurrent Neural networks.
Outcome:	The proposed model is comparable to the state-of-the-art without external lexical features on the SemEval-2010 dataset.

Copied to clipboard

Xuming Hu, Lijie Wen, Yusong Xu, Chenwei Zhang, Philip Yu

Towards a More Generalized Approach in Open Relation Extraction (2025.acl-long)

Challenge:	Existing methods for relation extraction use heuristics or distant-supervised annotations, but distant supervised methods make strong assumptions on entity cooccurrence without sufficient contexts.
Approach:	They propose a framework that exploits weak, self-supervised signals by leveraging large pretrained language models for adaptive clustering on contextualized relational features.
Outcome:	The proposed framework exploits weak, self-supervised signals on open-domain Relation Extraction . it bootstraps the self-supervised signals by improving contextualized features in relation classification .

Copied to clipboard

Qing Wang, Yuepei Li, Qiao Qiao, Kang Zhou, Qi Li

Verb Metaphor Detection via Contextual Relation Learning (2021.acl-long)

Challenge:	Existing OpenRE methods assume unlabeled data is a mixture of known and novel instances.
Approach:	They propose a generalized OpenRE setting that considers unlabeled data as a mixture of known and novel instances.
Outcome:	The proposed framework outperforms baselines in relation classification and clustering on three benchmark datasets.

Copied to clipboard

Wei Song, Shuhui Zhou, Ruiji Fu, Ting Liu, Lizhen Liu

Dependency-driven Relation Extraction with Attentive Graph Convolutional Networks (2021.acl-long)

Challenge:	Recent work on verb metaphor detection focuses on analyzing restricted forms of linguistic context.
Approach:	They propose a model which explicitly models the relation between a verb and its various contexts.
Outcome:	The proposed model gets competitive results compared with state-of-the-art approaches on the VUA, MOH-X and TroFi datasets.

Copied to clipboard

Yuanhe Tian, Guimin Chen, Yan Song, Xiang Wan

A Span-Based Model for Joint Overlapped and Discontinuous Named Entity Recognition (2021.acl-long)

Challenge:	Existing studies suffer from noise in dependency trees, which can cause confusions in relation extraction.
Approach:	They propose a dependency-driven approach for relation extraction with attentive graph convolutional networks . they apply an attention mechanism upon graph convolutional networks to different word dependencies .
Outcome:	The proposed approach outperforms previous studies on two English datasets and achieves state-of-the-art performance.

Copied to clipboard

Fei Li, ZhiChao Lin, Meishan Zhang, Donghong Ji

KLMo: Knowledge Graph Enhanced Pretrained Language Model with Fine-Grained Relationships (2021.findings-emnlp)

Challenge:	Existing models for named entity recognition (NER) focus on overlapped or discontinuous entities.
Approach:	They propose a span-based named entity recognition model that can recognize both overlapped and discontinuous entities jointly.
Outcome:	The proposed model can recognize overlapped and discontinuous entities jointly.

Copied to clipboard

Lei He, Suncong Zheng, Tao Yang, Feng Zhang

Syntax-Enhanced Pre-trained Model (2021.acl-long)

Challenge:	Existing knowledge-enhanced pretrained language models focus on entity information and ignore fine-grained relationships between entities.
Approach:	They propose to incorporate KG into the language learning process to obtain a KG-enhanced pretrained Language Model.
Outcome:	The proposed model improves on several knowledge-driven tasks, such as entity typing and relation classification, compared with the state-of-the-art knowledge-enhanced PLMs.

Copied to clipboard

Zenan Xu, Daya Guo, Duyu Tang, Qinliang Su, Linjun Shou, Ming Gong, Wanjun Zhong, Xiaojun Quan, Daxin Jiang, Nan Duan

Syntactic Text Processing

Challenge:	Existing methods that use syntax of text in pre-training and fine-tuning suffer from discrepancy between the two stages.
Approach:	They propose a model that utilizes the syntactic structure of text in pre-training and fine-tuning stages.
Outcome:	The proposed model achieves state-of-the-art on six public benchmark datasets.

Towards Realistic Few-Shot Relation Extraction (2021.emnlp-main)

Copied to clipboard

Sam Brody, Sichao Wu, Adrian Benton

PcMSP: A Dataset for Scientific Action Graphs Extraction from Polycrystalline Materials Synthesis Procedure Text (2022.findings-emnlp)

Challenge:	Recent studies have shown that few-shot relation classification models can be used to extract any relation of interest from a collection of text with only a few example instances.
Approach:	They propose to modify the training routine to encourage models to better discriminate between relations involving similar entity types.
Outcome:	The proposed models outperform human models on relation extraction tasks while relying on entity type information.

Copied to clipboard

Xianjun Yang, Ya Zhuo, Julia Zuo, Xinlu Zhang, Stephen Wilson, Linda Petzold

DISRPT: A Multilingual, Multi-domain, Cross-framework Benchmark for Discourse Processing (2024.lrec-main)

Challenge:	305 open access scientific articles are used for synthesis action graphs . lack of annotated data has hindered progress in this field .
Approach:	They propose to annotate Polycrystalline Materials Synthesis Procedures PcMSP from 305 open access scientific articles for the construction of synthesis action graphs.
Outcome:	The proposed dataset contains the synthesis sentences, entity mentions and intra-sentence relations extracted from the experimental paragraphs.

Copied to clipboard

Chloé Braud, Amir Zeldes, Laura Rivière, Yang Janet Liu, Philippe Muller, Damien Sileo, Tatsuya Aoyama

Text Classification

Challenge:	DISRPT is a multilingual, multi-domain, and cross-framework benchmark dataset for discourse processing.
Approach:	They present a multilingual, multi-domain, and cross-framework benchmark dataset for discourse processing that includes 13 languages and 24 corpora covering about 4 millions tokens and around 250,000 discourse relation instances from 4 discourse frameworks.
Outcome:	The DISRPT dataset includes data from 24 corpora covering about 4 millions tokens and around 250,000 discourse relation instances from 4 discourse frameworks.

KEPLET: Knowledge-Enhanced Pretrained Language Model with Topic Entity Awareness (2023.findings-emnlp)

Copied to clipboard

Yichuan Li, Jialong Han, Kyumin Lee, Chengyuan Ma, Benjamin Yao, Xiaohu Liu

Enhancing Multilingual Language Model with Massive Multilingual Knowledge Triples (2022.emnlp-main)

Challenge:	Pre-trained language models (PLMs) have shown their superiority by pre-training on unstructured text corpus and then fine-tuning on downstream tasks.
Approach:	They propose a Knowledge-Enhanced Pre-trained LanguagE model with Topic entity awareness that incorporates the interactions between tokens and mentioned entities in pre-training.
Outcome:	The proposed model incorporates the interactions between tokens and mentioned entities in pre-training and is more effective on entity-centric tasks.

Copied to clipboard

Linlin Liu, Xin Li, Ruidan He, Lidong Bing, Shafiq Joty, Luo Si

LegalDiscourse: Interpreting When Laws Apply and To Whom (2024.naacl-long)

Challenge:	Existing methods for language model pretraining use limited knowledge graph data for knowledge-intensive tasks.
Approach:	They propose to make better use of multilingual annotations and language agnostic properties of KG triples for pretraining LMs.
Outcome:	The proposed models show significant performance improvements on a wide range of knowledge-intensive cross-lingual tasks.

Copied to clipboard

Alexander Spangher, Zihan Xue, Te-Lin Wu, Mark Hansen, Jonathan May

Re-Cent: A Relation-Centric Framework for Joint Zero-Shot Relation Triplet Extraction (2025.coling-main)

Challenge:	Recent advances in NLP and information retrieval have already enabled practical applications.
Approach:	They propose a 'discourse' taxonomy for span-and-relation parsing of legal texts . they use a dataset of 602 state-level law paragraphs with 3,715 discourse spans and 1,671 relations to investigate the increase in liquor licenses and decrease in applicable laws.
Outcome:	The proposed model performs poorly at span identification and relation classification, but lags far below human level.

Copied to clipboard

Zehan Li, Fu Zhang, Kailun Lyu, Jingwei Cheng, Tianyue Peng

Low-Resource NLP

Challenge:	Existing methods to extract triplets from context often decompose into named entity recognition and relation classification, which may introduce error propagation.
Approach:	They propose a Relation-centric joint ZSRTE method which leverages unseen relation labels to extract triplets in one go.
Outcome:	The proposed method achieves state-of-the-art performance with fewer parameters and does not rely on synthetic data or manual labor.

FewRel: A Large-Scale Supervised Few-Shot Relation Classification Dataset with State-of-the-Art Evaluation (D18-1)

Copied to clipboard

Xu Han, Hao Zhu, Pengfei Yu, Ziyun Wang, Yuan Yao, Zhiyuan Liu, Maosong Sun

Low-Resource NLP

Challenge:	Empirical results show that even the most competitive few-shot learning models struggle on this task, especially as compared with humans.
Approach:	They propose a Few-Shot Relation Classification Dataset consisting of 70, 000 sentences on 100 relations derived from Wikipedia and annotated by crowdworkers.
Outcome:	The proposed methods perform well on the most competitive few-shot learning models, especially as compared with humans.

LUKE: Deep Contextualized Entity Representations with Entity-aware Self-attention (2020.emnlp-main)

Copied to clipboard

Ikuya Yamada, Akari Asai, Hiroyuki Shindo, Hideaki Takeda, Yuji Matsumoto

Multi-Perspective Document Revision (2022.coling-1)

Challenge:	Existing models for entity representations do not capture information in a knowledge base, and cannot represent entities that do not exist in the KB.
Approach:	They propose a pretrained contextualized representation of words and entities based on the bidirectional transformer.
Outcome:	The proposed model achieves impressive empirical performance on a wide range of entity-related tasks.

Copied to clipboard

Mana Ihori, Hiroshi Sato, Tomohiro Tanaka, Ryo Masumura

Syntactic Text Processing

Challenge:	a novel document revision task that revises multiple perspectives is proposed . grammatical error correction tasks have been studied in the natural language processing field .
Approach:	They propose a Japanese multi-perspective document revision task that revises multiple perspectives to improve the readability and clarity of a document.
Outcome:	The proposed model can be used to improve the readability and clarity of a document.

Direct Fact Retrieval from Knowledge Graphs without Entity Linking (2023.acl-long)

Copied to clipboard

Jinheon Baek, Alham Fikri Aji, Jens Lehmann, Sung Ju Hwang

From Examples to Rules: Neural Guided Rule Synthesis for Information Extraction (2022.lrec-1)

Challenge:	Existing methods to retrieve facts from Knowledge Graphs (KGs) require additional labels and may accumulate errors .
Approach:	They propose a framework that directly retrieves facts from KGs given input text based on their representational similarities.
Outcome:	The proposed framework outperforms baselines on multiple fact retrieval tasks.

Copied to clipboard

Robert Vacareanu, Marco A. Valenzuela-Escárcega, George Caique Gouveia Barbosa, Rebecca Sharp, Gustave Hahn-Powell, Mihai Surdeanu

Distilling Relation Embeddings from Pretrained Language Models (2021.emnlp-main)

Challenge:	a "deep learning tsunami" has brought tremendous improvements in performance to most NLP applications.
Approach:	They propose a method for rule synthesis from examples that combines the advantages of deep learning and rule-based methods.
Outcome:	The proposed method achieves state-of-the-art on 1-shot task and competitive performance in 5-shot scenario.

Copied to clipboard

Asahi Ushio, Jose Camacho-Collados, Steven Schockaert

HTMR: Hybrid Token Masking Reinforcement Learning with Verifiable Rewards for Event Argument Extraction with Multi-Perspective Reasoning (2026.acl-long)

Challenge:	Pre-trained language models capture a surprisingly rich amount of lexical knowledge, but it is unclear to what extent relation embeddings can be used to encode relational knowledge.
Approach:	They found that word vector differences capture lexical relations . relationship embeddings can be used to encode relational knowledge .
Outcome:	The results are highly competitive on analogy (unsupervised) and relation classification (supervised) benchmarks, even without any task-specific fine-tuning.

Copied to clipboard

Jianwen Luo, Yongkang Jin, Yu Hong, Jianmin Yao

Probing LLMs for Multilingual Discourse Generalization Through a Unified Label Set (2025.acl-long)

Challenge:	Recent work formulates EAE with large language models as a structured conditional generation task and applies Reinforcement Learning with Verifiable Rewards (RLVR) to optimize sequence-level event structures.
Approach:	They propose a method that selectively updates policy gradients on high-entropy forking tokens and event-critical tokens that define event structure.
Outcome:	The proposed method outperforms full-token and high-entropy only methods and transfers effectively as a plug-and-play approach to other tasks such as named entity recognition and relation classification.

Copied to clipboard

Florian Eichin, Yang Janet Liu, Barbara Plank, Michael A. Hedderich

Multilinguality

Challenge:	Existing work on discourse understanding is constrained by framework-dependent discourse representations.
Approach:	They examine whether large language models capture discourse knowledge that generalizes across languages and frameworks.
Outcome:	The proposed model can generalize discourse information across languages and frameworks.

Rationale-Enhanced Language Models are Better Continual Relation Learners (2023.emnlp-main)

Copied to clipboard

Weimin Xiong, Yifan Song, Peiyi Wang, Sujian Li

Tracing Relational Knowledge Recall in Large Language Models (2026.findings-acl)

Challenge:	Recent studies have found that catastrophic forgetting arises from the model’s lack of robustness against future analogous relations.
Approach:	They propose a multi-task rationale tuning strategy to help the model learn current relations robustly and conduct contrastive rationale replay to further distinguish analogous relations.
Outcome:	The proposed method outperforms the state-of-the-art models on two benchmarks.

Copied to clipboard

Nicholas Popovič, Michael Färber