English

Simple and Effective Paraphrastic Similarity from Parallel Translations

Computation and Language 2019-10-01 v1

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.

Keywords

Cite

@article{arxiv.1909.13872,
  title  = {Simple and Effective Paraphrastic Similarity from Parallel Translations},
  author = {John Wieting and Kevin Gimpel and Graham Neubig and Taylor Berg-Kirkpatrick},
  journal= {arXiv preprint arXiv:1909.13872},
  year   = {2019}
}

Comments

Published as a short paper at ACL 2019

R2 v1 2026-06-23T11:30:37.252Z