Do Neural Dialog Systems Use the Conversation History Effectively? An Empirical Study

Chinnadhurai Sankar, Sandeep Subramanian, Chris Pal, Sarath Chandar, Yoshua Bengio


Abstract
Neural generative models have been become increasingly popular when building conversational agents. They offer flexibility, can be easily adapted to new domains, and require minimal domain engineering. A common criticism of these systems is that they seldom understand or use the available dialog history effectively. In this paper, we take an empirical approach to understanding how these models use the available dialog history by studying the sensitivity of the models to artificially introduced unnatural changes or perturbations to their context at test time. We experiment with 10 different types of perturbations on 4 multi-turn dialog datasets and find that commonly used neural dialog architectures like recurrent and transformer-based seq2seq models are rarely sensitive to most perturbations such as missing or reordering utterances, shuffling words, etc. Also, by open-sourcing our code, we believe that it will serve as a useful diagnostic tool for evaluating dialog systems in the future.
Anthology ID:
P19-1004
Volume:
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2019
Address:
Florence, Italy
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
32–37
Language:
URL:
https://aclanthology.org/P19-1004
DOI:
10.18653/v1/P19-1004
Bibkey:
Copy Citation:
PDF:
https://aclanthology.org/P19-1004.pdf
Video:
 https://vimeo.com/383952222
Code
 chinnadhurai/ParlAI
Data
DailyDialogMutualFriendsPERSONA-CHAT