Boosting Knowledge Base Automatically via Few-Shot Relation Classification

Boosting Knowledge Base Automatically via Few-Shot Relation Classification

Relation classification (RC) aims at extracting structural information, i.e., triplets of two entities with a relation, from free texts, which is pivotal for automatic knowledge base construction. In this paper, we investigate a fully automatic method to train a RC model which facilitates to boost t...

Full description

Bibliographic Details
Main Authors: Ning Pang, Zhen Tan, Hao Xu, Weidong Xiao
Format: Article
Language:English
Published: Frontiers Media S.A. 2020-10-01
Series:Frontiers in Neurorobotics
Subjects:
knowledge base
relation classification
few-shot learning
distant supervision
multiple instance learning
Online Access:https://www.frontiersin.org/articles/10.3389/fnbot.2020.584192/full

Internet

https://www.frontiersin.org/articles/10.3389/fnbot.2020.584192/full

Similar Items