Enriching Word Vectors with Subword Information

TL;DR

This paper introduces a subword-based approach to learn word vectors that incorporate morphological information, improving representations especially for rare words across multiple languages.

Contribution

It proposes a fast skipgram model extension that represents words as bags of character n-grams, enabling better handling of rare and unseen words.

Findings

Achieves state-of-the-art performance on word similarity and analogy tasks

Effective across nine languages

Allows for fast training on large corpora

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.