Litcius/Paper detail

Coarse-to-Fine Pre-training for Named Entity Recognition

Mengge Xue, Bowen Yu, Zhenyu Zhang, Tingwen Liu, Yue Zhang, Bin Wang

202050 citationsDOIOpen Access PDF

Abstract

More recently, Named Entity Recognition has achieved great advances aided by pre-training approaches such as BERT.However, current pre-training techniques focus on building language modeling objectives to learn a general representation, ignoring the named entityrelated knowledge.To this end, we propose a NER-specific pre-training framework to inject coarse-to-fine automatically mined entity knowledge into pre-trained models.Specifically, we first warm-up the model via an entity span identification task by training it with Wikipedia anchors, which can be deemed as general-typed entities.Then we leverage the gazetteer-based distant supervision strategy to train the model extract coarse-grained typed entities.Finally, we devise a self-supervised auxiliary task to mine the fine-grained named entity knowledge via clustering.Empirical studies on three public NER datasets demonstrate that our framework achieves significant improvements against several pre-trained baselines, establishing the new state-of-the-art performance on three benchmarks.Besides, we show that our framework gains promising results without using human-labeled training data, demonstrating its effectiveness in labelfew and low-resource scenarios.

Topics & Concepts

Computer scienceNamed-entity recognitionLeverage (statistics)Cluster analysisArtificial intelligenceTask (project management)Named entityKnowledge baseMachine learningFocus (optics)Identification (biology)Entity linkingNatural language processingOpticsEconomicsManagementBotanyPhysicsBiologyTopic ModelingNatural Language Processing TechniquesText and Document Classification Technologies
Coarse-to-Fine Pre-training for Named Entity Recognition | Litcius