BORT: Back and Denoising Reconstruction for End-to-End Task-Oriented Dialog

Haipeng Sun, Junwei Bao, Youzheng Wu, Xiaodong He


Abstract
A typical end-to-end task-oriented dialog system transfers context into dialog state, and upon which generates a response, which usually faces the problem of error propagation from both previously generated inaccurate dialog states and responses, especially in low-resource scenarios. To alleviate these issues, we propose BORT, a back and denoising reconstruction approach for end-to-end task-oriented dialog system. Squarely, to improve the accuracy of dialog states, back reconstruction is used to reconstruct the original input context from the generated dialog states since inaccurate dialog states cannot recover the corresponding input context. To enhance the denoising capability of the model to reduce the impact of error propagation, denoising reconstruction is used to reconstruct the corrupted dialog state and response. Extensive experiments conducted on MultiWOZ 2.0 and CamRest676 show the effectiveness of BORT. Furthermore, BORT demonstrates its advanced capabilities in the zero-shot domain and low-resource scenarios.
Anthology ID:
2022.findings-naacl.166
Volume:
Findings of the Association for Computational Linguistics: NAACL 2022
Month:
July
Year:
2022
Address:
Seattle, United States
Editors:
Marine Carpuat, Marie-Catherine de Marneffe, Ivan Vladimir Meza Ruiz
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2156–2170
Language:
URL:
https://aclanthology.org/2022.findings-naacl.166
DOI:
10.18653/v1/2022.findings-naacl.166
Bibkey:
Cite (ACL):
Haipeng Sun, Junwei Bao, Youzheng Wu, and Xiaodong He. 2022. BORT: Back and Denoising Reconstruction for End-to-End Task-Oriented Dialog. In Findings of the Association for Computational Linguistics: NAACL 2022, pages 2156–2170, Seattle, United States. Association for Computational Linguistics.
Cite (Informal):
BORT: Back and Denoising Reconstruction for End-to-End Task-Oriented Dialog (Sun et al., Findings 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.findings-naacl.166.pdf
Software:
 2022.findings-naacl.166.software.zip
Video:
 https://aclanthology.org/2022.findings-naacl.166.mp4
Code
 jd-ai-research-nlp/bort
Data
MultiWOZ