Unsupervised Hypernymy Directionality Prediction Using Context Terms

Anonymous

Abstract: Hypernymy directionality prediction is an important task in Natural Language Processing due to its significant usages in natural language understanding and generation. Many supervised and unsupervised methods have been proposed for this task, but existing unsupervised methods do not leverage distributional pre-trained vectors from neural language models, as supervised methods typically do. In this paper, we present a simple yet effective unsupervised method for hypernymy directionality prediction that exploits neural pre-trained word vectors in context, based on the distributional informativeness hypothesis. Extensive experiments on seven datasets demonstrate that our method outperforms or achieves comparable performance to existing unsupervised and supervised methods.

Paper Type: short

Research Area: Semantics: Lexical

Languages Studied: English

Consent To Share Submission Details: On behalf of all authors, we agree to the terms above to share our submission details.