Abstract
Data augmentation seeks to manipulate the available data for training to improve the generalization ability of models. We investigate two data augmentation proxies, permutation and flipping, for neural dialog response selection task on various models over multiple datasets, including both Chinese and English languages. Different from standard data augmentation techniques, our method combines the original and synthesized data for prediction. Empirical results show that our approach can gain 1 to 3 recall-at-1 points over baseline models in both full-scale and small-scale settings.- Anthology ID:
- W18-5708
- Volume:
- Proceedings of the 2018 EMNLP Workshop SCAI: The 2nd International Workshop on Search-Oriented Conversational AI
- Month:
- October
- Year:
- 2018
- Address:
- Brussels, Belgium
- Editors:
- Aleksandr Chuklin, Jeff Dalton, Julia Kiseleva, Alexey Borisov, Mikhail Burtsev
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 52–58
- Language:
- URL:
- https://aclanthology.org/W18-5708
- DOI:
- 10.18653/v1/W18-5708
- Cite (ACL):
- Wenchao Du and Alan Black. 2018. Data Augmentation for Neural Online Chats Response Selection. In Proceedings of the 2018 EMNLP Workshop SCAI: The 2nd International Workshop on Search-Oriented Conversational AI, pages 52–58, Brussels, Belgium. Association for Computational Linguistics.
- Cite (Informal):
- Data Augmentation for Neural Online Chats Response Selection (Du & Black, EMNLP 2018)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-2/W18-5708.pdf
- Data
- Douban