Scene Restoring for Narrative Machine Reading Comprehension
Zhixing Tian, Yuanzhe Zhang, Kang Liu, Jun Zhao, Yantao Jia, Zhicheng Sheng
Abstract
This paper focuses on machine reading comprehension for narrative passages. Narrative passages usually describe a chain of events. When reading this kind of passage, humans tend to restore a scene according to the text with their prior knowledge, which helps them understand the passage comprehensively. Inspired by this behavior of humans, we propose a method to let the machine imagine a scene during reading narrative for better comprehension. Specifically, we build a scene graph by utilizing Atomic as the external knowledge and propose a novel Graph Dimensional-Iteration Network (GDIN) to encode the graph. We conduct experiments on the ROCStories, a dataset of Story Cloze Test (SCT), and CosmosQA, a dataset of multiple choice. Our method achieves state-of-the-art.- Anthology ID:
- 2020.emnlp-main.247
- Volume:
- Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
- Month:
- November
- Year:
- 2020
- Address:
- Online
- Editors:
- Bonnie Webber, Trevor Cohn, Yulan He, Yang Liu
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 3063–3073
- Language:
- URL:
- https://aclanthology.org/2020.emnlp-main.247
- DOI:
- 10.18653/v1/2020.emnlp-main.247
- Cite (ACL):
- Zhixing Tian, Yuanzhe Zhang, Kang Liu, Jun Zhao, Yantao Jia, and Zhicheng Sheng. 2020. Scene Restoring for Narrative Machine Reading Comprehension. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 3063–3073, Online. Association for Computational Linguistics.
- Cite (Informal):
- Scene Restoring for Narrative Machine Reading Comprehension (Tian et al., EMNLP 2020)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-2/2020.emnlp-main.247.pdf