Abstract
Despite the recent popularity of word embedding methods, there is only a small body of work exploring the limitations of these representations. In this paper, we consider one aspect of embedding spaces, namely their stability. We show that even relatively high frequency words (100-200 occurrences) are often unstable. We provide empirical evidence for how various factors contribute to the stability of word embeddings, and we analyze the effects of stability on downstream tasks.- Anthology ID:
- N18-1190
- Volume:
- Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)
- Month:
- June
- Year:
- 2018
- Address:
- New Orleans, Louisiana
- Editors:
- Marilyn Walker, Heng Ji, Amanda Stent
- Venue:
- NAACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 2092–2102
- Language:
- URL:
- https://aclanthology.org/N18-1190
- DOI:
- 10.18653/v1/N18-1190
- Cite (ACL):
- Laura Wendlandt, Jonathan K. Kummerfeld, and Rada Mihalcea. 2018. Factors Influencing the Surprising Instability of Word Embeddings. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), pages 2092–2102, New Orleans, Louisiana. Association for Computational Linguistics.
- Cite (Informal):
- Factors Influencing the Surprising Instability of Word Embeddings (Wendlandt et al., NAACL 2018)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-1/N18-1190.pdf
- Code
- laura-burdick/embeddingStability + additional community code
- Data
- New York Times Annotated Corpus