Abstract
Word embedding models typically learn two types of vectors: target word vectors and context word vectors. These vectors are normally learned such that they are predictive of some word co-occurrence statistic, but they are otherwise unconstrained. However, the words from a given language can be organized in various natural groupings, such as syntactic word classes (e.g. nouns, adjectives, verbs) and semantic themes (e.g. sports, politics, sentiment). Our hypothesis in this paper is that embedding models can be improved by explicitly imposing a cluster structure on the set of context word vectors. To this end, our model relies on the assumption that context word vectors are drawn from a mixture of von Mises-Fisher (vMF) distributions, where the parameters of this mixture distribution are jointly optimized with the word vectors. We show that this results in word vectors which are qualitatively different from those obtained with existing word embedding models. We furthermore show that our embedding model can also be used to learn high-quality document representations.- Anthology ID:
- P19-1321
- Volume:
- Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
- Month:
- July
- Year:
- 2019
- Address:
- Florence, Italy
- Editors:
- Anna Korhonen, David Traum, Lluís Màrquez
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 3319–3328
- Language:
- URL:
- https://aclanthology.org/P19-1321
- DOI:
- 10.18653/v1/P19-1321
- Cite (ACL):
- Shoaib Jameel and Steven Schockaert. 2019. Word and Document Embedding with vMF-Mixture Priors on Context Word Vectors. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 3319–3328, Florence, Italy. Association for Computational Linguistics.
- Cite (Informal):
- Word and Document Embedding with vMF-Mixture Priors on Context Word Vectors (Jameel & Schockaert, ACL 2019)
- PDF:
- https://preview.aclanthology.org/ingest-acl-2023-videos/P19-1321.pdf