Abstract
Word embeddings provide point representations of words containing useful semantic information. We introduce multimodal word distributions formed from Gaussian mixtures, for multiple word meanings, entailment, and rich uncertainty information. To learn these distributions, we propose an energy-based max-margin objective. We show that the resulting approach captures uniquely expressive semantic information, and outperforms alternatives, such as word2vec skip-grams, and Gaussian embeddings, on benchmark datasets such as word similarity and entailment.- Anthology ID:
- P17-1151
- Volume:
- Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Month:
- July
- Year:
- 2017
- Address:
- Vancouver, Canada
- Editors:
- Regina Barzilay, Min-Yen Kan
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1645–1656
- Language:
- URL:
- https://aclanthology.org/P17-1151
- DOI:
- 10.18653/v1/P17-1151
- Cite (ACL):
- Ben Athiwaratkun and Andrew Wilson. 2017. Multimodal Word Distributions. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1645–1656, Vancouver, Canada. Association for Computational Linguistics.
- Cite (Informal):
- Multimodal Word Distributions (Athiwaratkun & Wilson, ACL 2017)
- PDF:
- https://preview.aclanthology.org/ingest-acl-2023-videos/P17-1151.pdf
- Code
- benathi/word2gm + additional community code