Simple and Effective Paraphrastic Similarity from Parallel Translations

Code

• github.com/jwieting/paraphrastic-representations-at-scale
  pytorch★ 75
• github.com/acl-org/reviewer-paper-matching
  pytorch★ 0
• github.com/jwcmu/paraphrastic-sentence-embeddings
  pytorch★ 0
• github.com/jwieting/simple-and-effective-paraphrastic-similarity
  pytorch★ 0

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.

Tasks

Reproductions