Prompt-based Conservation Learning for Multi-hop Question Answering

Zhenyun Deng, Yonghua Zhu, Yang Chen, Qianqian Qi, Michael Witbrock, Patricia Riddle


Abstract
Multi-hop question answering (QA) requires reasoning over multiple documents to answer a complex question and provide interpretable supporting evidence. However, providing supporting evidence is not enough to demonstrate that a model has performed the desired reasoning to reach the correct answer. Most existing multi-hop QA methods fail to answer a large fraction of sub-questions, even if their parent questions are answered correctly. In this paper, we propose the Prompt-based Conservation Learning (PCL) framework for multi-hop QA, which acquires new knowledge from multi-hop QA tasks while conserving old knowledge learned on single-hop QA tasks, mitigating forgetting. Specifically, we first train a model on existing single-hop QA tasks, and then freeze this model and expand it by allocating additional sub-networks for the multi-hop QA task. Moreover, to condition pre-trained language models to stimulate the kind of reasoning required for specific multi-hop questions, we learn soft prompts for the novel sub-networks to perform type-specific reasoning. Experimental results on the HotpotQA benchmark show that PCL is competitive for multi-hop QA and retains good performance on the corresponding single-hop sub-questions, demonstrating the efficacy of PCL in mitigating knowledge loss by forgetting.
Anthology ID:
2022.coling-1.154
Volume:
Proceedings of the 29th International Conference on Computational Linguistics
Month:
October
Year:
2022
Address:
Gyeongju, Republic of Korea
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
1791–1800
Language:
URL:
https://aclanthology.org/2022.coling-1.154
DOI:
Bibkey:
Cite (ACL):
Zhenyun Deng, Yonghua Zhu, Yang Chen, Qianqian Qi, Michael Witbrock, and Patricia Riddle. 2022. Prompt-based Conservation Learning for Multi-hop Question Answering. In Proceedings of the 29th International Conference on Computational Linguistics, pages 1791–1800, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
Cite (Informal):
Prompt-based Conservation Learning for Multi-hop Question Answering (Deng et al., COLING 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.coling-1.154.pdf
Data
2WikiMultiHopQAHotpotQASQuAD