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.
- Publication:
-
arXiv e-prints
- Pub Date:
- September 2019
- DOI:
- 10.48550/arXiv.1909.13872
- arXiv:
- arXiv:1909.13872
- Bibcode:
- 2019arXiv190913872W
- Keywords:
-
- Computer Science - Computation and Language
- E-Print:
- Published as a short paper at ACL 2019