Language-Agnostic Transformers and Assessing ChatGPT-Based Query Rewriting for Multilingual Document-Grounded QA

Srinivas Gowriraj, Soham Dinesh Tiwari, Mitali Potnis, Srijan Bansal, Teruko Mitamura, Eric Nyberg


Abstract
The DialDoc 2023 shared task has expanded the document-grounded dialogue task to encompass multiple languages, despite having limited annotated data. This paper assesses the effectiveness of both language-agnostic and language-aware paradigms for multilingual pre-trained transformer models in a bi-encoder-based dense passage retriever (DPR), concluding that the language-agnostic approach is superior. Additionally, the study investigates the impact of query rewriting techniques using large language models, such as ChatGPT, on multilingual, document-grounded question-answering systems. The experiments conducted demonstrate that, for the examples examined, query rewriting does not enhance performance compared to the original queries. This failure is due to topic switching in final dialogue turns and irrelevant topics being considered for query rewriting.
Anthology ID:
2023.dialdoc-1.11
Volume:
Proceedings of the Third DialDoc Workshop on Document-grounded Dialogue and Conversational Question Answering
Month:
July
Year:
2023
Address:
Toronto, Canada
Venue:
dialdoc
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
101–108
Language:
URL:
https://aclanthology.org/2023.dialdoc-1.11
DOI:
Bibkey:
Cite (ACL):
Srinivas Gowriraj, Soham Dinesh Tiwari, Mitali Potnis, Srijan Bansal, Teruko Mitamura, and Eric Nyberg. 2023. Language-Agnostic Transformers and Assessing ChatGPT-Based Query Rewriting for Multilingual Document-Grounded QA. In Proceedings of the Third DialDoc Workshop on Document-grounded Dialogue and Conversational Question Answering, pages 101–108, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Language-Agnostic Transformers and Assessing ChatGPT-Based Query Rewriting for Multilingual Document-Grounded QA (Gowriraj et al., dialdoc 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/nodalida-main-page/2023.dialdoc-1.11.pdf