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...

Celý popis

Podrobná bibliografie

Hlavní autoři:	Tiantian Chen, Nianbin Wang, Ming He, Liu Sun
Médium:	Artigo
Jazyk:	Inglês
Vydáno:	IEEE 2020-01-01
Edice:	IEEE Access
Témata:	Relation extraction distant supervision reinforcement learning label denoising
On-line přístup:	https://ieeexplore.ieee.org/document/9079540/
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!