Simple and Effective Paraphrastic Similarity from Parallel Translations

Abstract

We present a model and methodology for learning paraphrastic sentence embeddings directly from bitext, removing the time-consuming intermediate step of creating paraphrase corpora. Further, we show that the resulting model can be applied to cross-lingual tasks where it both outperforms and is orders of magnitude faster than more complex state-of-the-art baselines.

Published as a short paper at ACL 2019

Cited by in corpus (2)

• Self-training Improves Pre-training for Natural Language Understanding
• Disentangling Semantics and Syntax in Sentence Embeddings with Pre-trained Language Models