Litcius/Paper detail

HiCLRE: A Hierarchical Contrastive Learning Framework for Distantly Supervised Relation Extraction

Dongyang Li, Taolin Zhang, Nan Hu, Chengyu Wang, Xiaofeng He

2022Findings of the Association for Computational Linguistics: ACL 202237 citationsDOIOpen Access PDF

Abstract

Distant supervision assumes that any sentence containing the same entity pairs reflects identical relationships. Previous works of distantly supervised relation extraction (DSRE) task generally focus on sentence-level or bag-level denoising techniques independently, neglecting the explicit interaction with cross levels. In this paper, we propose a Hierarchical Contrastive Learning Framework for Distantly Supervised Relation Extraction (HiCLRE) to reduce noisy sentences, which integrate the global structural information and local fine-grained interaction. Specifically, we propose a three-level hierarchical learning framework to interact with cross levels, generating the de-noising context-aware representations via adapting the existing multihead self-attention, named Multi-Granularity Recontextualization. Meanwhile, pseudo positive samples are also provided in the specific level for contrastive learning via a dynamic gradient-based data augmentation strategy, named Dynamic Gradient Adversarial Perturbation. Experiments demonstrate that Hi-CLRE significantly outperforms strong baselines in various mainstream DSRE datasets.

Topics & Concepts

Computer scienceArtificial intelligenceGranularityRelationship extractionSentenceRelation (database)Natural language processingContext (archaeology)Supervised learningFocus (optics)Machine learningInformation extractionArtificial neural networkData miningOperating systemBiologyPaleontologyOpticsPhysicsTopic ModelingNatural Language Processing TechniquesSentiment Analysis and Opinion Mining