Abstract
Given a word, what is the most frequent sense in which it occurs in a given corpus? Most Frequent Sense (MFS) is a strong baseline for unsupervised word sense disambiguation. If we have large amounts of sense-annotated corpora, MFS can be trivially created. However, sense-annotated corpora are a rarity. In this paper, we propose a method which can compute MFS from raw corpora. Our approach iteratively exploits the semantic congruity among related words in corpus. Our method performs better compared to another similar work.- Anthology ID:
- 2018.gwc-1.34
- Volume:
- Proceedings of the 9th Global Wordnet Conference
- Month:
- January
- Year:
- 2018
- Address:
- Nanyang Technological University (NTU), Singapore
- Venue:
- GWC
- SIG:
- Publisher:
- Global Wordnet Association
- Note:
- Pages:
- 293–297
- Language:
- URL:
- https://aclanthology.org/2018.gwc-1.34
- DOI:
- Cite (ACL):
- Kevin Patel and Pushpak Bhattacharyya. 2018. An Iterative Approach for Unsupervised Most Frequent Sense Detection using WordNet and Word Embeddings. In Proceedings of the 9th Global Wordnet Conference, pages 293–297, Nanyang Technological University (NTU), Singapore. Global Wordnet Association.
- Cite (Informal):
- An Iterative Approach for Unsupervised Most Frequent Sense Detection using WordNet and Word Embeddings (Patel & Bhattacharyya, GWC 2018)
- PDF:
- https://preview.aclanthology.org/starsem-semeval-split/2018.gwc-1.34.pdf