Abstract
Lexical relations describe how meanings of terms relate to each other. Typical examples include hypernymy, synonymy, meronymy, etc. Automatic distinction of lexical relations is vital for NLP applications, and also challenging due to the lack of contextual signals to discriminate between such relations. In this work, we present a neural representation learning model to distinguish lexical relations among term pairs based on Hyperspherical Relation Embeddings (SphereRE). Rather than learning embeddings for individual terms, the model learns representations of relation triples by mapping them to the hyperspherical embedding space, where relation triples of different lexical relations are well separated. Experiments over several benchmarks confirm SphereRE outperforms state-of-the-arts.- Anthology ID:
- P19-1169
- Original:
- P19-1169v1
- Version 2:
- P19-1169v2
- Volume:
- Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
- Month:
- July
- Year:
- 2019
- Address:
- Florence, Italy
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1727–1737
- Language:
- URL:
- https://aclanthology.org/P19-1169
- DOI:
- 10.18653/v1/P19-1169
- Cite (ACL):
- Chengyu Wang, Xiaofeng He, and Aoying Zhou. 2019. SphereRE: Distinguishing Lexical Relations with Hyperspherical Relation Embeddings. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 1727–1737, Florence, Italy. Association for Computational Linguistics.
- Cite (Informal):
- SphereRE: Distinguishing Lexical Relations with Hyperspherical Relation Embeddings (Wang et al., ACL 2019)
- PDF:
- https://preview.aclanthology.org/paclic-22-ingestion/P19-1169.pdf
- Data
- EVALution