Abstract
Multi-hop reading comprehension requires an ability to reason across multiple documents. On the one hand, deep learning approaches only implicitly encode query-related information into distributed embeddings which fail to uncover the discrete relational reasoning process to infer the correct answer. On the other hand, logic-based approaches provide interpretable rules to infer the target answer, but mostly work on structured data where entities and relations are well-defined. In this paper, we propose a deep-learning based inductive logic reasoning method that firstly extracts query-related (candidate-related) information, and then conducts logic reasoning among the filtered information by inducing feasible rules that entail the target relation. The reasoning process is accomplished via attentive memories with novel differentiable logic operators. To demonstrate the effectiveness of our model, we evaluate it on two reading comprehension datasets, namely WikiHop and MedHop.- Anthology ID:
- 2022.acl-long.343
- Volume:
- Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Month:
- May
- Year:
- 2022
- Address:
- Dublin, Ireland
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 4999–5009
- Language:
- URL:
- https://aclanthology.org/2022.acl-long.343
- DOI:
- 10.18653/v1/2022.acl-long.343
- Cite (ACL):
- Wenya Wang and Sinno Pan. 2022. Deep Inductive Logic Reasoning for Multi-Hop Reading Comprehension. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 4999–5009, Dublin, Ireland. Association for Computational Linguistics.
- Cite (Informal):
- Deep Inductive Logic Reasoning for Multi-Hop Reading Comprehension (Wang & Pan, ACL 2022)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/2022.acl-long.343.pdf
- Data
- MedHop, WikiHop