Term Definitions Help Hypernymy Detection

Wenpeng Yin, Dan Roth
2018 Proceedings of the Seventh Joint Conference on Lexical and Computational Semantics  
Existing methods of hypernymy detection mainly rely on statistics over a big corpus, either mining some co-occurring patterns like "animals such as cats" or embedding words of interest into context-aware vectors. These approaches are therefore limited by the availability of a large enough corpus that can cover all terms of interest and provide sufficient contextual information to represent their meaning. In this work, we propose a new paradigm, HYPERDEF, for hypernymy detection -expressing word
more » ... on -expressing word meaning by encoding word definitions, along with context driven representation. This has two main benefits: (i) Definitional sentences express (sense-specific) corpus-independent meanings of words, hence definition-driven approaches enable strong generalization -once trained, the model is expected to work well in opendomain testbeds; (ii) Global context from a large corpus and definitions provide complementary information for words. Consequently, our model, HYPERDEF, once trained on taskagnostic data, gets state-of-the-art results in multiple benchmarks 1 .
doi:10.18653/v1/s18-2025 dblp:conf/starsem/YinR18 fatcat:gxhoxumxevgydf7c6w6ezfgsdi