Word Usage Similarity Estimation with Sentence Representations and Automatic Substitutes
This work addresses usage similarity estimation for natural language processing, but it is incremental as it builds on existing methods with enhancements.
The paper tackled the problem of estimating semantic proximity between word instances in different contexts by applying contextualized embeddings and supervised models, achieving state-of-the-art performance on benchmark datasets for both graded and binary similarity.
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.