Learning Word Embeddings without Context Vectors

Alexey Zobnin, Evgenia Elistratova


Abstract
Most word embedding algorithms such as word2vec or fastText construct two sort of vectors: for words and for contexts. Naive use of vectors of only one sort leads to poor results. We suggest using indefinite inner product in skip-gram negative sampling algorithm. This allows us to use only one sort of vectors without loss of quality. Our “context-free” cf algorithm performs on par with SGNS on word similarity datasets
Anthology ID:
W19-4329
Volume:
Proceedings of the 4th Workshop on Representation Learning for NLP (RepL4NLP-2019)
Month:
August
Year:
2019
Address:
Florence, Italy
Editors:
Isabelle Augenstein, Spandana Gella, Sebastian Ruder, Katharina Kann, Burcu Can, Johannes Welbl, Alexis Conneau, Xiang Ren, Marek Rei
Venue:
RepL4NLP
SIG:
SIGREP
Publisher:
Association for Computational Linguistics
Note:
Pages:
244–249
Language:
URL:
https://aclanthology.org/W19-4329
DOI:
10.18653/v1/W19-4329
Bibkey:
Cite (ACL):
Alexey Zobnin and Evgenia Elistratova. 2019. Learning Word Embeddings without Context Vectors. In Proceedings of the 4th Workshop on Representation Learning for NLP (RepL4NLP-2019), pages 244–249, Florence, Italy. Association for Computational Linguistics.
Cite (Informal):
Learning Word Embeddings without Context Vectors (Zobnin & Elistratova, RepL4NLP 2019)
Copy Citation:
PDF:
https://aclanthology.org/W19-4329.pdf