LMVE at SemEval-2020 Task 4: Commonsense Validation and Explanation using Pretraining Language Model

Abstract

This paper describes our submission to subtask a and b of SemEval-2020 Task 4. For subtask a, we use a ALBERT based model with improved input form to pick out the common sense statement from two statement candidates. For subtask b, we use a multiple choice model enhanced by hint sentence mechanism to select the reason from given options about why a statement is against common sense. Besides, we propose a novel transfer learning strategy between subtasks which help improve the performance. The accuracy scores of our system are 95.6/94.9 on official test set2 and rank 7th/2nd on Post-Evaluation leaderboard.