TA-MAMC at SemEval-2021 Task 4: Task-adaptive Pretraining and Multi-head Attention for Abstract Meaning Reading Comprehension

Jing Zhang, Yimeng Zhuang, Yinpei Su


Abstract
This paper describes our system used in the SemEval-2021 Task4 Reading Comprehension of Abstract Meaning, achieving 1st for subtask 1 and 2nd for subtask 2 on the leaderboard. We propose an ensemble of ELECTRA-based models with task-adaptive pretraining and a multi-head attention multiple-choice classifier on top of the pre-trained model. The main contributions of our system are 1) revealing the performance discrepancy of different transformer-based pretraining models on the downstream task, 2) presentation of an efficient method to generate large task-adaptive corpora for pretraining. We also investigated several pretraining strategies and contrastive learning objectives. Our system achieves a test accuracy of 95.11 and 94.89 on subtask 1 and subtask 2 respectively.
Anthology ID:
2021.semeval-1.5
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:
51–58
Language:
URL:
https://aclanthology.org/2021.semeval-1.5
DOI:
10.18653/v1/2021.semeval-1.5
Bibkey:
Cite (ACL):
Jing Zhang, Yimeng Zhuang, and Yinpei Su. 2021. TA-MAMC at SemEval-2021 Task 4: Task-adaptive Pretraining and Multi-head Attention for Abstract Meaning Reading Comprehension. In Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021), pages 51–58, Online. Association for Computational Linguistics.
Cite (Informal):
TA-MAMC at SemEval-2021 Task 4: Task-adaptive Pretraining and Multi-head Attention for Abstract Meaning Reading Comprehension (Zhang et al., SemEval 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.semeval-1.5.pdf
Data
GLUEMultiNLINEWSROOMReCAM