Abstract
Discriminating lexical relations among distributionally similar words has always been a challenge for natural language processing (NLP) community. In this paper, we investigate whether the network embedding of distributional thesaurus can be effectively utilized to detect co-hyponymy relations. By extensive experiments over three benchmark datasets, we show that the vector representation obtained by applying node2vec on distributional thesaurus outperforms the state-of-the-art models for binary classification of co-hyponymy vs. hypernymy, as well as co-hyponymy vs. meronymy, by huge margins.- Anthology ID:
- 2020.lrec-1.707
- Volume:
- Proceedings of the Twelfth Language Resources and Evaluation Conference
- Month:
- May
- Year:
- 2020
- Address:
- Marseille, France
- Editors:
- Nicoletta Calzolari, Frédéric Béchet, Philippe Blache, Khalid Choukri, Christopher Cieri, Thierry Declerck, Sara Goggi, Hitoshi Isahara, Bente Maegaard, Joseph Mariani, Hélène Mazo, Asuncion Moreno, Jan Odijk, Stelios Piperidis
- Venue:
- LREC
- SIG:
- Publisher:
- European Language Resources Association
- Note:
- Pages:
- 5766–5771
- Language:
- English
- URL:
- https://aclanthology.org/2020.lrec-1.707
- DOI:
- Cite (ACL):
- Abhik Jana, Nikhil Reddy Varimalla, and Pawan Goyal. 2020. Using Distributional Thesaurus Embedding for Co-hyponymy Detection. In Proceedings of the Twelfth Language Resources and Evaluation Conference, pages 5766–5771, Marseille, France. European Language Resources Association.
- Cite (Informal):
- Using Distributional Thesaurus Embedding for Co-hyponymy Detection (Jana et al., LREC 2020)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-5/2020.lrec-1.707.pdf