ReCAM@IITK at SemEval-2021 Task 4: BERT and ALBERT based Ensemble for Abstract Word Prediction
Abhishek Mittal, Ashutosh Modi · 2021
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.* WC -Wrong Confident -27 such examples * WN -Wrong Confused -109 such examples * CC -Correct Confident -446 such examples * CN -Correct Confused -269 such examples