Abstract
Explainable multi-hop question answering (QA) not only predicts answers but also identifies rationales, i. e. subsets of input sentences used to derive the answers. Existing methods rely on supervision for both answers and rationales. This problem has been extensively studied under the supervised setting, where both answer and rationale annotations are given. Because rationale annotations are expensive to collect and not always available, recent efforts have been devoted to developing methods that do not rely on supervision for rationales. However, such methods have limited capacities in modeling interactions between sentences, let alone reasoning across multiple documents. This work proposes a principled, probabilistic approach for training explainable multi-hop QA systems without rationale supervision. Our approach performs multi-hop reasoning by explicitly modeling rationales as sets, enabling the model to capture interactions between documents and sentences within a document. Experimental results show that our approach is more accurate at selecting rationales than the previous methods, while maintaining similar accuracy in predicting answers.- Anthology ID:
- 2023.emnlp-main.1001
- Volume:
- Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
- Month:
- December
- Year:
- 2023
- Address:
- Singapore
- Editors:
- Houda Bouamor, Juan Pino, Kalika Bali
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 16119–16130
- Language:
- URL:
- https://aclanthology.org/2023.emnlp-main.1001
- DOI:
- 10.18653/v1/2023.emnlp-main.1001
- Cite (ACL):
- Wenting Zhao, Justin Chiu, Claire Cardie, and Alexander Rush. 2023. Hop, Union, Generate: Explainable Multi-hop Reasoning without Rationale Supervision. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 16119–16130, Singapore. Association for Computational Linguistics.
- Cite (Informal):
- Hop, Union, Generate: Explainable Multi-hop Reasoning without Rationale Supervision (Zhao et al., EMNLP 2023)
- PDF:
- https://preview.aclanthology.org/naacl24-info/2023.emnlp-main.1001.pdf