Factors Influencing the Surprising Instability of Word Embeddings

Laura Wendlandt, Jonathan K. Kummerfeld, Rada Mihalcea


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
Bibkey:
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)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-1/N18-1190.pdf
Code
 laura-burdick/embeddingStability +  additional community code
Data
New York Times Annotated Corpus