Reducing Wrong Labels for Distantly Supervised Relation Extraction With Reinforcement Learning

Relation extraction (RE) aims to mine semantic relations between entity pairs from plain texts, which plays an important role in various natural language processing (NLP) tasks. However, the existing methods in distant supervision (DS) are sensitive to bags and fail to handle sentence-level relation...

Descripció completa

Dades bibliogràfiques

Autors principals:	Tiantian Chen, Nianbin Wang, Ming He, Liu Sun
Format:	Artigo
Idioma:	Inglês
Publicat:	IEEE 2020-01-01
Col·lecció:	IEEE Access
Matèries:	Relation extraction distant supervision reinforcement learning label denoising
Accés en línia:	https://ieeexplore.ieee.org/document/9079540/
Etiquetes:	Afegir etiqueta Sense etiquetes, Sigues el primer a etiquetar aquest registre!