Abstract
This paper describes our system for SemEval-2018 Task 11: Machine Comprehension using Commonsense Knowledge. We use Three-way Attentive Networks (TriAN) to model interactions between the passage, question and answers. To incorporate commonsense knowledge, we augment the input with relation embedding from the graph of general knowledge ConceptNet. As a result, our system achieves state-of-the-art performance with 83.95% accuracy on the official test data. Code is publicly available at https://github.com/intfloat/commonsense-rc.- Anthology ID:
- S18-1120
- Volume:
- Proceedings of the 12th International Workshop on Semantic Evaluation
- Month:
- June
- Year:
- 2018
- Address:
- New Orleans, Louisiana
- Editors:
- Marianna Apidianaki, Saif M. Mohammad, Jonathan May, Ekaterina Shutova, Steven Bethard, Marine Carpuat
- Venue:
- SemEval
- SIG:
- SIGLEX
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 758–762
- Language:
- URL:
- https://aclanthology.org/S18-1120
- DOI:
- 10.18653/v1/S18-1120
- Cite (ACL):
- Liang Wang, Meng Sun, Wei Zhao, Kewei Shen, and Jingming Liu. 2018. Yuanfudao at SemEval-2018 Task 11: Three-way Attention and Relational Knowledge for Commonsense Machine Comprehension. In Proceedings of the 12th International Workshop on Semantic Evaluation, pages 758–762, New Orleans, Louisiana. Association for Computational Linguistics.
- Cite (Informal):
- Yuanfudao at SemEval-2018 Task 11: Three-way Attention and Relational Knowledge for Commonsense Machine Comprehension (Wang et al., SemEval 2018)
- PDF:
- https://preview.aclanthology.org/naacl-24-ws-corrections/S18-1120.pdf
- Code
- intfloat/commonsense-rc + additional community code
- Data
- ConceptNet, RACE