Abstract
We propose a new CogQA framework for multi-hop reading comprehension question answering in web-scale documents. Founded on the dual process theory in cognitive science, the framework gradually builds a cognitive graph in an iterative process by coordinating an implicit extraction module (System 1) and an explicit reasoning module (System 2). While giving accurate answers, our framework further provides explainable reasoning paths. Specifically, our implementation based on BERT and graph neural network efficiently handles millions of documents for multi-hop reasoning questions in the HotpotQA fullwiki dataset, achieving a winning joint F1 score of 34.9 on the leaderboard, compared to 23.1 of the best competitor.- Anthology ID:
- P19-1259
- Volume:
- Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
- Month:
- July
- Year:
- 2019
- Address:
- Florence, Italy
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 2694–2703
- Language:
- URL:
- https://aclanthology.org/P19-1259
- DOI:
- 10.18653/v1/P19-1259
- Cite (ACL):
- Ming Ding, Chang Zhou, Qibin Chen, Hongxia Yang, and Jie Tang. 2019. Cognitive Graph for Multi-Hop Reading Comprehension at Scale. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 2694–2703, Florence, Italy. Association for Computational Linguistics.
- Cite (Informal):
- Cognitive Graph for Multi-Hop Reading Comprehension at Scale (Ding et al., ACL 2019)
- PDF:
- https://preview.aclanthology.org/paclic-22-ingestion/P19-1259.pdf
- Code
- THUDM/CogQA + additional community code
- Data
- HotpotQA, SQuAD