Learning to Flip the Sentiment of Reviews from Non-Parallel Corpora

Canasai Kruengkrai


Abstract
Flipping sentiment while preserving sentence meaning is challenging because parallel sentences with the same content but different sentiment polarities are not always available for model learning. We introduce a method for acquiring imperfectly aligned sentences from non-parallel corpora and propose a model that learns to minimize the sentiment and content losses in a fully end-to-end manner. Our model is simple and offers well-balanced results across two domains: Yelp restaurant and Amazon product reviews.
Anthology ID:
D19-1659
Volume:
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
Month:
November
Year:
2019
Address:
Hong Kong, China
Editors:
Kentaro Inui, Jing Jiang, Vincent Ng, Xiaojun Wan
Venues:
EMNLP | IJCNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
6311–6316
Language:
URL:
https://aclanthology.org/D19-1659
DOI:
10.18653/v1/D19-1659
Bibkey:
Cite (ACL):
Canasai Kruengkrai. 2019. Learning to Flip the Sentiment of Reviews from Non-Parallel Corpora. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 6311–6316, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
Learning to Flip the Sentiment of Reviews from Non-Parallel Corpora (Kruengkrai, EMNLP-IJCNLP 2019)
Copy Citation:
PDF:
https://aclanthology.org/D19-1659.pdf