Enriching Word Vectors with Subword Information

Piotr Bojanowski, Edouard Grave, Armand Joulin, Tomas Mikolov


Abstract
Continuous word representations, trained on large unlabeled corpora are useful for many natural language processing tasks. Popular models that learn such representations ignore the morphology of words, by assigning a distinct vector to each word. This is a limitation, especially for languages with large vocabularies and many rare words. In this paper, we propose a new approach based on the skipgram model, where each word is represented as a bag of character n-grams. A vector representation is associated to each character n-gram; words being represented as the sum of these representations. Our method is fast, allowing to train models on large corpora quickly and allows us to compute word representations for words that did not appear in the training data. We evaluate our word representations on nine different languages, both on word similarity and analogy tasks. By comparing to recently proposed morphological word representations, we show that our vectors achieve state-of-the-art performance on these tasks.
Anthology ID:
Q17-1010
Volume:
Transactions of the Association for Computational Linguistics, Volume 5
Month:
Year:
2017
Address:
Cambridge, MA
Editors:
Lillian Lee, Mark Johnson, Kristina Toutanova
Venue:
TACL
SIG:
Publisher:
MIT Press
Note:
Pages:
135–146
Language:
URL:
https://aclanthology.org/Q17-1010
DOI:
10.1162/tacl_a_00051
Bibkey:
Cite (ACL):
Piotr Bojanowski, Edouard Grave, Armand Joulin, and Tomas Mikolov. 2017. Enriching Word Vectors with Subword Information. Transactions of the Association for Computational Linguistics, 5:135–146.
Cite (Informal):
Enriching Word Vectors with Subword Information (Bojanowski et al., TACL 2017)
Copy Citation:
PDF:
https://aclanthology.org/Q17-1010.pdf
Video:
 https://aclanthology.org/Q17-1010.mp4
Code
 facebookresearch/fastText +  additional community code
Data
100DOH