BIBI System Description: Building with CNNs and Breaking with Deep Reinforcement Learning

Yitong Li, Trevor Cohn, Timothy Baldwin


Abstract
This paper describes our submission to the sentiment analysis sub-task of “Build It, Break It: The Language Edition (BIBI)”, on both the builder and breaker sides. As a builder, we use convolutional neural nets, trained on both phrase and sentence data. As a breaker, we use Q-learning to learn minimal change pairs, and apply a token substitution method automatically. We analyse the results to gauge the robustness of NLP systems.
Anthology ID:
W17-5404
Volume:
Proceedings of the First Workshop on Building Linguistically Generalizable NLP Systems
Month:
September
Year:
2017
Address:
Copenhagen, Denmark
Venue:
WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
27–32
Language:
URL:
https://aclanthology.org/W17-5404
DOI:
10.18653/v1/W17-5404
Bibkey:
Cite (ACL):
Yitong Li, Trevor Cohn, and Timothy Baldwin. 2017. BIBI System Description: Building with CNNs and Breaking with Deep Reinforcement Learning. In Proceedings of the First Workshop on Building Linguistically Generalizable NLP Systems, pages 27–32, Copenhagen, Denmark. Association for Computational Linguistics.
Cite (Informal):
BIBI System Description: Building with CNNs and Breaking with Deep Reinforcement Learning (Li et al., 2017)
Copy Citation:
PDF:
https://aclanthology.org/W17-5404.pdf