Technical Report on Shared Task in DialDoc21

Jiapeng Li, Mingda Li, Longxuan Ma, Wei-Nan Zhang, Ting Liu


Abstract
We participate in the DialDoc Shared Task sub-task 1 (Knowledge Identification). The task requires identifying the grounding knowledge in form of a document span for the next dialogue turn. We employ two well-known pre-trained language models (RoBERTa and ELECTRA) to identify candidate document spans and propose a metric-based ensemble method for span selection. Our methods include data augmentation, model pre-training/fine-tuning, post-processing, and ensemble. On the submission page, we rank 2nd based on the average of normalized F1 and EM scores used for the final evaluation. Specifically, we rank 2nd on EM and 3rd on F1.
Anthology ID:
2021.dialdoc-1.7
Volume:
Proceedings of the 1st Workshop on Document-grounded Dialogue and Conversational Question Answering (DialDoc 2021)
Month:
August
Year:
2021
Address:
Online
Venues:
ACL | IJCNLP | dialdoc
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
52–56
Language:
URL:
https://aclanthology.org/2021.dialdoc-1.7
DOI:
10.18653/v1/2021.dialdoc-1.7
Bibkey:
Cite (ACL):
Jiapeng Li, Mingda Li, Longxuan Ma, Wei-Nan Zhang, and Ting Liu. 2021. Technical Report on Shared Task in DialDoc21. In Proceedings of the 1st Workshop on Document-grounded Dialogue and Conversational Question Answering (DialDoc 2021), pages 52–56, Online. Association for Computational Linguistics.
Cite (Informal):
Technical Report on Shared Task in DialDoc21 (Li et al., dialdoc 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.dialdoc-1.7.pdf
Data
CoQA