papers AI Learner
The Github is limit! Click to go to the new site.

Word Usage Similarity Estimation with Sentence Representations and Automatic Substitutes

2019-05-20
Aina Garí Soler, Marianna Apidianaki, Alexandre Allauzen

Abstract

Usage similarity estimation addresses the semantic proximity of word instances in different contexts. We apply contextualized (ELMo and BERT) word and sentence embeddings to this task, and propose supervised models that leverage these representations for prediction. Our models are further assisted by lexical substitute annotations automatically assigned to word instances by context2vec, a neural model that relies on a bidirectional LSTM. We perform an extensive comparison of existing word and sentence representations on benchmark datasets addressing both graded and binary similarity. The best performing models outperform previous methods in both settings.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1905.08377

PDF

http://arxiv.org/pdf/1905.08377


Comments

Content