Abstract
Progress in statistical paraphrase generation has been hindered for a long time by the lack of large monolingual parallel corpora. In this paper, we adapt the neural machine translation approach to paraphrase generation and perform transfer learning from the closely related task of entailment generation. We evaluate the model on the Microsoft Research Paraphrase (MSRP) corpus and show that the model is able to generate sentences that capture part of the original meaning, but fails to pick up on important words or to show large lexical variation.- Anthology ID:
- W17-3542
- Volume:
- Proceedings of the 10th International Conference on Natural Language Generation
- Month:
- September
- Year:
- 2017
- Address:
- Santiago de Compostela, Spain
- Editors:
- Jose M. Alonso, Alberto Bugarín, Ehud Reiter
- Venue:
- INLG
- SIG:
- SIGGEN
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 257–261
- Language:
- URL:
- https://aclanthology.org/W17-3542
- DOI:
- 10.18653/v1/W17-3542
- Cite (ACL):
- Florin Brad and Traian Rebedea. 2017. Neural Paraphrase Generation using Transfer Learning. In Proceedings of the 10th International Conference on Natural Language Generation, pages 257–261, Santiago de Compostela, Spain. Association for Computational Linguistics.
- Cite (Informal):
- Neural Paraphrase Generation using Transfer Learning (Brad & Rebedea, INLG 2017)
- PDF:
- https://preview.aclanthology.org/ingest-acl-2023-videos/W17-3542.pdf
- Data
- SNLI