CAiRE in DialDoc21: Data Augmentation for Information Seeking Dialogue System

Yan Xu, Etsuko Ishii, Genta Indra Winata, Zhaojiang Lin, Andrea Madotto, Zihan Liu, Peng Xu, Pascale Fung


Abstract
Information-seeking dialogue systems, including knowledge identification and response generation, aim to respond to users with fluent, coherent, and informative responses based on users’ needs, which. To tackle this challenge, we utilize data augmentation methods and several training techniques with the pre-trained language models to learn a general pattern of the task and thus achieve promising performance. In DialDoc21 competition, our system achieved 74.95 F1 score and 60.74 Exact Match score in subtask 1, and 37.72 SacreBLEU score in subtask 2. Empirical analysis is provided to explain the effectiveness of our approaches.
Anthology ID:
2021.dialdoc-1.6
Volume:
Proceedings of the 1st Workshop on Document-grounded Dialogue and Conversational Question Answering (DialDoc 2021)
Month:
August
Year:
2021
Address:
Online
Venue:
dialdoc
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
46–51
Language:
URL:
https://aclanthology.org/2021.dialdoc-1.6
DOI:
10.18653/v1/2021.dialdoc-1.6
Bibkey:
Cite (ACL):
Yan Xu, Etsuko Ishii, Genta Indra Winata, Zhaojiang Lin, Andrea Madotto, Zihan Liu, Peng Xu, and Pascale Fung. 2021. CAiRE in DialDoc21: Data Augmentation for Information Seeking Dialogue System. In Proceedings of the 1st Workshop on Document-grounded Dialogue and Conversational Question Answering (DialDoc 2021), pages 46–51, Online. Association for Computational Linguistics.
Cite (Informal):
CAiRE in DialDoc21: Data Augmentation for Information Seeking Dialogue System (Xu et al., dialdoc 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.dialdoc-1.6.pdf
Code
 HLTCHKUST/CAiRE_in_DialDoc21
Data
MRQASearchQATriviaQA