AUTHOR=Pang Ning , Tan Zhen , Xu Hao , Xiao Weidong TITLE=Boosting Knowledge Base Automatically via Few-Shot Relation Classification JOURNAL=Frontiers in Neurorobotics VOLUME=14 YEAR=2020 URL=https://www.frontiersin.org/journals/neurorobotics/articles/10.3389/fnbot.2020.584192 DOI=10.3389/fnbot.2020.584192 ISSN=1662-5218 ABSTRACT=
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 the knowledge base. Traditional RC models cannot extract new relations unseen during training since they define RC as a multiclass classification problem. The recent development of few-shot learning (FSL) provides a feasible way to accommodate to fresh relation types with a handful of examples. However, it requires a moderately large amount of training data to learn a promising few-shot RC model, which consumes expensive human labor. This issue recalls a kind of weak supervision methods, dubbed distant supervision (DS), which can generate the training data automatically. To this end, we propose to investigate the task of