Abstract
Transferring DGD models from high-resource languages to low-resource languages is a meaningful but challenging task. Being able to provide multilingual responses to multilingual documents further complicates the task. This paper describes our method at DialDoc23 Shared Task (Document-Grounded Dialogue and Conversational Question Answering) for generate responses based on the most relevant passage retrieved. We divide it into three steps of retrieval, re-ranking and generation. Our methods include negative sample augmentation, prompt learning, pseudo-labeling and ensemble. On the submission page, we rank 2nd based on the sum of token-level F1, SacreBleu and Rouge-L scores used for the final evaluation, and get the total score of 210.25.- Anthology ID:
- 2023.dialdoc-1.3
- Volume:
- Proceedings of the Third DialDoc Workshop on Document-grounded Dialogue and Conversational Question Answering
- Month:
- July
- Year:
- 2023
- Address:
- Toronto, Canada
- Editors:
- Smaranda Muresan, Vivian Chen, Kennington Casey, Vandyke David, Dethlefs Nina, Inoue Koji, Ekstedt Erik, Ultes Stefan
- Venue:
- dialdoc
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 30–35
- Language:
- URL:
- https://aclanthology.org/2023.dialdoc-1.3
- DOI:
- 10.18653/v1/2023.dialdoc-1.3
- Cite (ACL):
- Xiaocheng Zhang, Huang Qing, and Fu Lin. 2023. Exploration of multilingual prompts in document-grounded dialogue. In Proceedings of the Third DialDoc Workshop on Document-grounded Dialogue and Conversational Question Answering, pages 30–35, Toronto, Canada. Association for Computational Linguistics.
- Cite (Informal):
- Exploration of multilingual prompts in document-grounded dialogue (Zhang et al., dialdoc 2023)
- PDF:
- https://preview.aclanthology.org/ingest-acl-2023-videos/2023.dialdoc-1.3.pdf