ECNU_ICA_1 SemEval-2021 Task 4: Leveraging Knowledge-enhanced Graph Attention Networks for Reading Comprehension of Abstract Meaning

Pingsheng Liu, Linlin Wang, Qian Zhao, Hao Chen, Yuxi Feng, Xin Lin, Liang He


Abstract
This paper describes our system for SemEval-2021 Task 4: Reading Comprehension of Abstract Meaning. To accomplish this task, we utilize the Knowledge-Enhanced Graph Attention Network (KEGAT) architecture with a novel semantic space transformation strategy. It leverages heterogeneous knowledge to learn adequate evidences, and seeks for an effective semantic space of abstract concepts to better improve the ability of a machine in understanding the abstract meaning of natural language. Experimental results show that our system achieves strong performance on this task in terms of both imperceptibility and nonspecificity.
Anthology ID:
2021.semeval-1.20
Volume:
Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021)
Month:
August
Year:
2021
Address:
Online
Venue:
SemEval
SIGs:
SIGSEM | SIGLEX
Publisher:
Association for Computational Linguistics
Note:
Pages:
183–188
Language:
URL:
https://aclanthology.org/2021.semeval-1.20
DOI:
10.18653/v1/2021.semeval-1.20
Bibkey:
Cite (ACL):
Pingsheng Liu, Linlin Wang, Qian Zhao, Hao Chen, Yuxi Feng, Xin Lin, and Liang He. 2021. ECNU_ICA_1 SemEval-2021 Task 4: Leveraging Knowledge-enhanced Graph Attention Networks for Reading Comprehension of Abstract Meaning. In Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021), pages 183–188, Online. Association for Computational Linguistics.
Cite (Informal):
ECNU_ICA_1 SemEval-2021 Task 4: Leveraging Knowledge-enhanced Graph Attention Networks for Reading Comprehension of Abstract Meaning (Liu et al., SemEval 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.semeval-1.20.pdf
Data
ConceptNet