Abstract
Complex questions in reading comprehension tasks require integrating information from multiple sentences. In this work, to answer such questions involving temporal and causal relations, we generate event graphs from text based on dependencies, and rank answers by aligning event graphs. In particular, the alignments are constrained by graph-based reasoning to ensure temporal and causal agreement. Our focused approach self-adaptively complements existing solutions; it is automatically triggered only when applicable. Experiments on RACE and MCTest show that state-of-the-art methods are notably improved by using our approach as an add-on.- Anthology ID:
- C18-1069
- Volume:
- Proceedings of the 27th International Conference on Computational Linguistics
- Month:
- August
- Year:
- 2018
- Address:
- Santa Fe, New Mexico, USA
- Editors:
- Emily M. Bender, Leon Derczynski, Pierre Isabelle
- Venue:
- COLING
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 806–817
- Language:
- URL:
- https://aclanthology.org/C18-1069
- DOI:
- Cite (ACL):
- Yawei Sun, Gong Cheng, and Yuzhong Qu. 2018. Reading Comprehension with Graph-based Temporal-Casual Reasoning. In Proceedings of the 27th International Conference on Computational Linguistics, pages 806–817, Santa Fe, New Mexico, USA. Association for Computational Linguistics.
- Cite (Informal):
- Reading Comprehension with Graph-based Temporal-Casual Reasoning (Sun et al., COLING 2018)
- PDF:
- https://preview.aclanthology.org/naacl24-info/C18-1069.pdf
- Data
- MCTest, RACE