Paper: Distributional Lexical Entailment by Topic Coherence

ACL ID E14-1054
Title Distributional Lexical Entailment by Topic Coherence
Venue Annual Meeting of The European Chapter of The Association of Computational Linguistics
Session Main Conference
Year 2014

Automatic detection of lexical entailment, or hypernym detection, is an important NLP task. Recent hypernym detection measures have been based on the Distri- butional Inclusion Hypothesis (DIH). This paper assumes that the DIH sometimes fails, and investigates other ways of quan- tifying the relationship between the co- occurrence contexts of two terms. We con- sider the top features in a context vector as a topic, and introduce a new entailment detection measure based on Topic Coher- ence (TC). Our measure successfully de- tects hypernyms, and a TC-based family of measures contributes to multi-way rela- tion classification.