CUHK at SemEval-2020 Task 4: CommonSense Explanation, Reasoning and Prediction with Multi-task Learning

TL;DR

This paper presents a multi-task learning system based on BERT for the SemEval-2020 ComVE challenge, effectively validating, reasoning, and explaining commonsense sentences with high accuracy and interpretability.

Contribution

It introduces an interpretable multi-task BERT-based system that jointly addresses validation, reasoning, and explanation of commonsense sentences, inspired by cognitive studies.

Findings

Achieved 92.9% accuracy in validation subtask

Achieved 89.7% accuracy in reasoning subtask

Achieved BLEU score of 12.9 in explanation subtask

Abstract

This paper describes our system submitted to task 4 of SemEval 2020: Commonsense Validation and Explanation (ComVE) which consists of three sub-tasks. The task is to directly validate the given sentence whether or not it makes sense and require the model to explain it. Based on BERTarchitecture with a multi-task setting, we propose an effective and interpretable "Explain, Reason and Predict" (ERP) system to solve the three sub-tasks about commonsense: (a) Validation, (b)Reasoning, and (c) Explanation. Inspired by cognitive studies of common sense, our system first generates a reason or understanding of the sentences and then chooses which one statement makes sense, which is achieved by multi-task learning. During the post-evaluation, our system has reached 92.9% accuracy in subtask A (rank 11), 89.7% accuracy in subtask B (rank 9), andBLEU score of 12.9 in subtask C (rank 8)