Learning Paraphrastic Sentence Embeddings from Back-Translated Bitext
Abstract
We consider the problem of learning general-purpose, paraphrastic sentence embeddings in the setting of Wieting et al. (2016b). We use neural machine translation to generate sentential paraphrases via back-translation of bilingual sentence pairs. We evaluate the paraphrase pairs by their ability to serve as training data for learning paraphrastic sentence embeddings. We find that the data quality is stronger than prior work based on bitext and on par with manually-written English paraphrase pairs, with the advantage that our approach can scale up to generate large training sets for many languages and domains. We experiment with several language pairs and data sources, and develop a variety of data filtering techniques. In the process, we explore how neural machine translation output differs from human-written sentences, finding clear differences in length, the amount of repetition, and the use of rare words.- Anthology ID:
- D17-1026
- Volume:
- Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
- Month:
- September
- Year:
- 2017
- Address:
- Copenhagen, Denmark
- Editors:
- Martha Palmer, Rebecca Hwa, Sebastian Riedel
- Venue:
- EMNLP
- SIG:
- SIGDAT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 274–285
- Language:
- URL:
- https://aclanthology.org/D17-1026
- DOI:
- 10.18653/v1/D17-1026
- Cite (ACL):
- John Wieting, Jonathan Mallinson, and Kevin Gimpel. 2017. Learning Paraphrastic Sentence Embeddings from Back-Translated Bitext. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 274–285, Copenhagen, Denmark. Association for Computational Linguistics.
- Cite (Informal):
- Learning Paraphrastic Sentence Embeddings from Back-Translated Bitext (Wieting et al., EMNLP 2017)
- PDF:
- https://preview.aclanthology.org/teach-a-man-to-fish/D17-1026.pdf