Abstract
SemEval task 4 aims to find a proper option from multiple candidates to resolve the task of machine reading comprehension. Most existing approaches propose to concat question and option together to form a context-aware model. However, we argue that straightforward concatenation can only provide a coarse-grained context for the MRC task, ignoring the specific positions of the option relative to the question. In this paper, we propose a novel MRC model by filling options into the question to produce a fine-grained context (defined as summary) which can better reveal the relationship between option and question. We conduct a series of experiments on the given dataset, and the results show that our approach outperforms other counterparts to a large extent.- Anthology ID:
- 2021.semeval-1.110
- Volume:
- Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021)
- Month:
- August
- Year:
- 2021
- Address:
- Online
- Editors:
- Alexis Palmer, Nathan Schneider, Natalie Schluter, Guy Emerson, Aurelie Herbelot, Xiaodan Zhu
- Venue:
- SemEval
- SIG:
- SIGLEX
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 827–832
- Language:
- URL:
- https://aclanthology.org/2021.semeval-1.110
- DOI:
- 10.18653/v1/2021.semeval-1.110
- Cite (ACL):
- Zhixiang Chen, Yikun Lei, Pai Liu, and Guibing Guo. 2021. NEUer at SemEval-2021 Task 4: Complete Summary Representation by Filling Answers into Question for Matching Reading Comprehension. In Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021), pages 827–832, Online. Association for Computational Linguistics.
- Cite (Informal):
- NEUer at SemEval-2021 Task 4: Complete Summary Representation by Filling Answers into Question for Matching Reading Comprehension (Chen et al., SemEval 2021)
- PDF:
- https://preview.aclanthology.org/ingest-acl-2023-videos/2021.semeval-1.110.pdf
- Data
- DREAM, MultiNLI, RACE, ReCAM