Abstract
A standard word embedding algorithm, such as word2vec and glove, makes a strong assumption that words are likely to be semantically related only if they co-occur locally within a window of fixed size. However, this strong assumption may not capture the semantic association between words that co-occur frequently but non-locally within documents. In this paper, we propose a graph-based word embedding method, named ‘word-node2vec’. By relaxing the strong constraint of locality, our method is able to capture both the local and non-local co-occurrences. Word-node2vec constructs a graph where every node represents a word and an edge between two nodes represents a combination of both local (e.g. word2vec) and document-level co-occurrences. Our experiments show that word-node2vec outperforms word2vec and glove on a range of different tasks, such as predicting word-pair similarity, word analogy and concept categorization.- Anthology ID:
- N19-1109
- Volume:
- Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
- Month:
- June
- Year:
- 2019
- Address:
- Minneapolis, Minnesota
- Editors:
- Jill Burstein, Christy Doran, Thamar Solorio
- Venue:
- NAACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1041–1051
- Language:
- URL:
- https://aclanthology.org/N19-1109
- DOI:
- 10.18653/v1/N19-1109
- Cite (ACL):
- Procheta Sen, Debasis Ganguly, and Gareth Jones. 2019. Word-Node2Vec: Improving Word Embedding with Document-Level Non-Local Word Co-occurrences. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 1041–1051, Minneapolis, Minnesota. Association for Computational Linguistics.
- Cite (Informal):
- Word-Node2Vec: Improving Word Embedding with Document-Level Non-Local Word Co-occurrences (Sen et al., NAACL 2019)
- PDF:
- https://preview.aclanthology.org/emnlp22-frontmatter/N19-1109.pdf