ReCAM@IITK at SemEval-2021 Task 4: BERT and ALBERT based Ensemble for Abstract Word Prediction

Abhishek Mittal, Ashutosh Modi


Abstract
This paper describes our system for Task 4 of SemEval-2021: Reading Comprehension of Abstract Meaning (ReCAM). We participated in all subtasks where the main goal was to predict an abstract word missing from a statement. We fine-tuned the pre-trained masked language models namely BERT and ALBERT and used an Ensemble of these as our submitted system on Subtask 1 (ReCAM-Imperceptibility) and Subtask 2 (ReCAM-Nonspecificity). For Subtask 3 (ReCAM-Intersection), we submitted the ALBERT model as it gives the best results. We tried multiple approaches and found that Masked Language Modeling(MLM) based approach works the best.
Anthology ID:
2021.semeval-1.19
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:
175–182
Language:
URL:
https://aclanthology.org/2021.semeval-1.19
DOI:
10.18653/v1/2021.semeval-1.19
Bibkey:
Cite (ACL):
Abhishek Mittal and Ashutosh Modi. 2021. ReCAM@IITK at SemEval-2021 Task 4: BERT and ALBERT based Ensemble for Abstract Word Prediction. In Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021), pages 175–182, Online. Association for Computational Linguistics.
Cite (Informal):
ReCAM@IITK at SemEval-2021 Task 4: BERT and ALBERT based Ensemble for Abstract Word Prediction (Mittal & Modi, SemEval 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.semeval-1.19.pdf
Code
 amittal151/SemEval-2021-Task4_models
Data
ReCAM