Enriching Word Vectors with Subword Information

By Piotr Bojanowski, Edouard Grave, Armand Joulin, Tomas Mikolov. 2016

10,838 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Natural Language Processing, Representation & Self-Supervised Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Mohit Bansal
  2. Luke S. Zettlemoyer
  3. Percy Liang
  4. Graham Neubig
  5. Jianfeng Gao
  6. Noah A. Smith
  7. Yejin Choi
  8. Kyunghyun Cho

In Natural Language Processing

  1. Mohit Bansal
  2. Graham Neubig
  3. Luke S. Zettlemoyer
  4. Yejin Choi
  5. Percy Liang
  6. Jianfeng Gao
  7. Noah A. Smith
  8. Kyunghyun Cho

In Representation & Self-Supervised Learning

  1. Sebastian Ruder
  2. Graham Neubig
  3. Ivan Vulic
  4. Hinrich Schütze
  5. Yoshua Bengio
  6. Iryna Gurevych
  7. Samuel R. Bowman
  8. Percy Liang

Citations in the corpus