目录
4、Universal Information Extraction
1、Named Entity Recognition
[1] Robust Self-Augmentation for Named Entity Recognition with Meta Reweighting
[2] ITA: Image-Text Alignments for Multi-Modal Named Entity Recognition
[3] Dynamic Gazetteer Integration in Multilingual Models for Cross-Lingual and Cross-Domain Named Entity Recognition
[4] Sentence-Level Resampling for Named Entity Recognition
[5] Hero-Gang Neural Model For Named Entity Recognition
[7] On the Use of External Data for Spoken Named Entity Recognition
[8] Label Refinement via Contrastive Learning for Distantly-Supervised Named Entity Recognition
[9] Delving Deep into Regularity: A Simple but Effective Method for Chinese Named Entity Recognition
[10] MultiNER: A Multilingual, Multi-Genre and Fine-Grained Dataset for Named Entity Recognition
[11] NER-MQMRC: Formulating Named Entity Recognition as Multi Question Machine Reading Comprehension
2、Relation Extraction
2.1 Document RE
[12] Few-Shot Document-Level Relation Extraction
[13] Document-Level Relation Extraction with Sentences Importance Estimation and Focusing
[14] Modeling Explicit Task Interactions in Document-Level Joint Entity and Relation Extraction
[15] Relation-Specific Attentions over Entity Mentions for Enhanced Document-Level Relation Extraction
[16] SAIS: Supervising and Augmenting Intermediate Steps for Document-Level Relation Extraction
2.2 Few-shot or Zero-shot
[12] Few-Shot Document-Level Relation Extraction
[17] RCL: Relation Contrastive Learning for Zero-Shot Relation Extraction
[18] HiURE: Hierarchical Exemplar Contrastive Learning for Unsupervised Relation Extraction
[19] Learn from Relation Information: Towards Prototype Representation Rectification for Few-Shot Relation Extraction
2.3 Constrative Learning
[18] HiURE: Hierarchical Exemplar Contrastive Learning for Unsupervised Relation Extraction
[17] RCL: Relation Contrastive Learning for Zero-Shot Relation Extraction
2.4 Distant Supervision
[19] Hierarchical Relation-Guided Type-Sentence Alignment for Long-Tail Relation Extraction with Distant Supervision
2.5 Others
[20] Modeling Multi-Granularity Hierarchical Features for Relation Extraction
[21] A Dataset for N-ary Relation Extraction of Drug Combinations
[22] Should We Rely on Entity Mentions for Relation Extraction? Debiasing Relation Extraction with Counterfactual Analysis
[23] Generic and Trend-aware Curricula for Relation Extraction in Text Graphs
[24] Learning Discriminative Representations for Open Relation Extraction with Instance Ranking and Label Calibration
[25] GraphCache: Message Passing as Caching for Sentence-Level Relation Extraction
[26] Good Visual Guidance Make A Better Extractor: Hierarchical Visual Prefix for Multimodal Entity and Relation Extraction
[27] Dependency Position Encoding for Relation Extraction
3、Event Extraction
[29] Cross-Lingual Event Detection via Optimized Adversarial Training
[30] A Two-Stream AMR-enhanced Model for Document-level Event Argument Extraction
[31] RAAT: Relation-Augmented Attention Transformer for Relation Modeling in Document-Level Event Extraction
[32] DocEE: A Large-Scale and Fine-grained Benchmark for Document-level Event Extraction
[33] Contrastive Representation Learning for Cross-Document Coreference Resolution of Events and Entities
[34] Document-Level Event Argument Extraction by Leveraging Redundant Information and Closed Boundary Loss
[35] MINION: a Large-Scale and Diverse Dataset for Multilingual Event Detection
[36] Event Schema Induction with Double Graph Autoencoders
[37] DEGREE: A Data-Efficient Generation-Based Event Extraction Model
[38] Go Back in Time: Generating Flashbacks in Stories with Event Plots and Temporal Prompts
[39] Improving Consistency with Event Awareness for Document-Level Argument Extraction
[40] Zero-Shot Event Detection Based on Ordered Contrastive Learning and Prompt-Based Prediction
[41] Textual Entailment for Event Argument Extraction: Zero- and Few-Shot with Multi-Source Learning
[42] Event Detection for Suicide Understanding
[43] Extracting Temporal Event Relation with Syntax-guided Graph Transformer
4、Universal Information Extraction
[44] Joint Extraction of Entities, Relations, and Events via Modeling Inter-Instance and Inter-Label Dependencies