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.

Keywords

Computer scienceWord (group theory)Natural language processingArtificial intelligenceCharacter (mathematics)Similarity (geometry)AnalogyRepresentation (politics)Language modelSpeech recognitionLinguisticsMathematics

Affiliated Institutions

Related Publications

Publication Info

Year
2017
Type
article
Volume
5
Pages
135-146
Citations
9444
Access
Closed

External Links

View on DOI.org

Social Impact

Altmetric
PlumX Metrics

Social media, news, blog, policy document mentions

Citation Metrics

9444
OpenAlex

Cite This

Piotr Bojanowski, Édouard Grave, Armand Joulin et al. (2017). Enriching Word Vectors with Subword Information. Transactions of the Association for Computational Linguistics , 5 , 135-146. https://doi.org/10.1162/tacl_a_00051

Identifiers

DOI
10.1162/tacl_a_00051