Abstract
Word Sense Induction (WSI) is the task of grouping of occurrences of an ambiguous word according to their meaning. In this work, we improve the approach to WSI proposed by Amrami and Goldberg (2018) based on clustering of lexical substitutes for an ambiguous word in a particular context obtained from neural language models. Namely, we propose methods for combining information from left and right context and similarity to the ambiguous word, which result in generating more accurate substitutes than the original approach. Our simple yet efficient improvement establishes a new state-of-the-art on WSI datasets for two languages. Besides, we show improvements to the original approach on a lexical substitution dataset.- Anthology ID:
- R19-1008
- Volume:
- Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2019)
- Month:
- September
- Year:
- 2019
- Address:
- Varna, Bulgaria
- Editors:
- Ruslan Mitkov, Galia Angelova
- Venue:
- RANLP
- SIG:
- Publisher:
- INCOMA Ltd.
- Note:
- Pages:
- 62–70
- Language:
- URL:
- https://aclanthology.org/R19-1008
- DOI:
- 10.26615/978-954-452-056-4_008
- Cite (ACL):
- Nikolay Arefyev, Boris Sheludko, and Alexander Panchenko. 2019. Combining Lexical Substitutes in Neural Word Sense Induction. In Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2019), pages 62–70, Varna, Bulgaria. INCOMA Ltd..
- Cite (Informal):
- Combining Lexical Substitutes in Neural Word Sense Induction (Arefyev et al., RANLP 2019)
- PDF:
- https://preview.aclanthology.org/emnlp-22-attachments/R19-1008.pdf