Multi-Task Learning of Query Generation and Classification for Generative Conversational Question Rewriting

Sarawoot Kongyoung, Craig MacDonald, Iadh Ounis


Abstract
In conversational search settings, users ask questions and receive answers as part of a conversation. The ambiguity in the questions is a common challenge, which can be effectively addressed by leveraging contextual information from the conversation history. In this context, determining topic continuity and reformulating questions into well-defined queries are crucial tasks. Previous approaches have typically addressed these tasks either as a classification task in the case of topic continuity or as a text generation task for question reformulation. However, no prior work has combined both tasks to effectively identify ambiguous questions as part of a conversation. In this paper, we propose a Multi-Task Learning (MTL) approach that uses a text generation model for both question rewriting and classification. Our models, based on BART and T5, are trained to rewrite conversational questions and identify follow-up questions simultaneously. We evaluate our approach on multiple test sets and demonstrate that it outperforms single-task learning baselines on the three LIF test sets, with statistically significant improvements ranging from +3.5% to +10.5% in terms of F1 and Micro-F1 scores. We also show that our approach outperforms single-task question rewriting models in passage retrieval on a large OR-QuAC test set.
Anthology ID:
2023.findings-emnlp.913
Original:
2023.findings-emnlp.913v1
Version 2:
2023.findings-emnlp.913v2
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2023
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
13667–13678
Language:
URL:
https://aclanthology.org/2023.findings-emnlp.913
DOI:
10.18653/v1/2023.findings-emnlp.913
Bibkey:
Cite (ACL):
Sarawoot Kongyoung, Craig MacDonald, and Iadh Ounis. 2023. Multi-Task Learning of Query Generation and Classification for Generative Conversational Question Rewriting. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 13667–13678, Singapore. Association for Computational Linguistics.
Cite (Informal):
Multi-Task Learning of Query Generation and Classification for Generative Conversational Question Rewriting (Kongyoung et al., Findings 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/naacl-24-ws-corrections/2023.findings-emnlp.913.pdf