# Term Definitions Help Hypernymy Detection

arXiv: https://arxiv.org/abs/1806.04532 · HTML: https://mlsanity.com/paper/1806.04532/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Jun 2018.

## Built on by (most cited first, 3 of 3)

- [Enquire One's Parent and Child Before Decision: Fully Exploit Hierarchical Structure for Self-Supervised Taxonomy Expansion](https://mlsanity.com/paper/2101.11268/) (2021)
- [Find Parent then Label Children: A Two-stage Taxonomy Completion Method with Pre-trained Language Model](https://mlsanity.com/paper/2406.17739/) (2024)
- [Inferring Scientific Cross-Document Coreference and Hierarchy with Definition-Augmented Relational Reasoning](https://mlsanity.com/paper/2409.15113/) (2024)

## Abstract (arXiv)

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 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 open-domain testbeds; (ii) Global context from a large corpus and definitions provide complementary information for words. Consequently, our model, HyperDef, once trained on task-agnostic data, gets state-of-the-art results in multiple benchmarks