Explaining and Generalizing Skip-Gram through Exponential Family Principal Component Analysis

Ryan Cotterell, Adam Poliak, Benjamin Van Durme, Jason Eisner


Abstract
The popular skip-gram model induces word embeddings by exploiting the signal from word-context coocurrence. We offer a new interpretation of skip-gram based on exponential family PCA-a form of matrix factorization to generalize the skip-gram model to tensor factorization. In turn, this lets us train embeddings through richer higher-order coocurrences, e.g., triples that include positional information (to incorporate syntax) or morphological information (to share parameters across related words). We experiment on 40 languages and show our model improves upon skip-gram.
Anthology ID:
E17-2028
Volume:
Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers
Month:
April
Year:
2017
Address:
Valencia, Spain
Editors:
Mirella Lapata, Phil Blunsom, Alexander Koller
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
175–181
Language:
URL:
https://preview.aclanthology.org/build-pipeline-with-new-library/E17-2028/
DOI:
Bibkey:
Cite (ACL):
Ryan Cotterell, Adam Poliak, Benjamin Van Durme, and Jason Eisner. 2017. Explaining and Generalizing Skip-Gram through Exponential Family Principal Component Analysis. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers, pages 175–181, Valencia, Spain. Association for Computational Linguistics.
Cite (Informal):
Explaining and Generalizing Skip-Gram through Exponential Family Principal Component Analysis (Cotterell et al., EACL 2017)
Copy Citation:
PDF:
https://preview.aclanthology.org/build-pipeline-with-new-library/E17-2028.pdf
Data
Universal Dependencies