English

Contextual Salience for Fast and Accurate Sentence Vectors

Computation and Language 2020-11-03 v6

Abstract

Unsupervised vector representations of sentences or documents are a major building block for many language tasks such as sentiment classification. However, current methods are uninterpretable and slow or require large training datasets. Recent word vector-based proposals implicitly assume that distances in a word embedding space are equally important, regardless of context. We introduce contextual salience (CoSal), a measure of word importance that uses the distribution of context vectors to normalize distances and weights. CoSal relies on the insight that unusual word vectors disproportionately affect phrase vectors. A bag-of-words model with CoSal-based weights produces accurate unsupervised sentence or document representations for classification, requiring little computation to evaluate and only a single covariance calculation to ``train." CoSal supports small contexts, out-of context words and outperforms SkipThought on most benchmarks, beats tf-idf on all benchmarks, and is competitive with the unsupervised state-of-the-art.

Keywords

Cite

@article{arxiv.1803.08493,
  title  = {Contextual Salience for Fast and Accurate Sentence Vectors},
  author = {Eric Zelikman and Richard Socher},
  journal= {arXiv preprint arXiv:1803.08493},
  year   = {2020}
}