Reducing Wrong Labels for Distantly Supervised Relation Extraction With Reinforcement Learning

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...

Full description

Bibliographic Details
Main Authors: Tiantian Chen, Nianbin Wang, Ming He, Liu Sun
Format: Article
Language:English
Published: IEEE 2020-01-01
Series:IEEE Access
Subjects:
Relation extraction
distant supervision
reinforcement learning
label denoising
Online Access:https://ieeexplore.ieee.org/document/9079540/

Internet

https://ieeexplore.ieee.org/document/9079540/

Similar Items