CS-NLP team at SemEval-2020 Task 4: Evaluation of State-of-the-art NLP Deep Learning Architectures on Commonsense Reasoning Task

TL;DR

This paper evaluates various deep learning architectures on a commonsense reasoning task, achieving high accuracy and demonstrating the effectiveness of reformulating classification as multiple choice questions.

Contribution

It introduces a novel approach of converting classification tasks into multiple choice questions to improve performance on commonsense reasoning benchmarks.

Findings

Achieved 96.06% accuracy on the first subtask.

Ranked within top six teams for identifying reasons for nonsensical statements.

Used GPT-2 for generating explanations with promising results.

Abstract

In this paper, we investigate a commonsense inference task that unifies natural language understanding and commonsense reasoning. We describe our attempt at SemEval-2020 Task 4 competition: Commonsense Validation and Explanation (ComVE) challenge. We discuss several state-of-the-art deep learning architectures for this challenge. Our system uses prepared labeled textual datasets that were manually curated for three different natural language inference subtasks. The goal of the first subtask is to test whether a model can distinguish between natural language statements that make sense and those that do not make sense. We compare the performance of several language models and fine-tuned classifiers. Then, we propose a method inspired by question/answering tasks to treat a classification problem as a multiple choice question task to boost the performance of our experimental results (96.06%), which is significantly better than the baseline. For the second subtask, which is to select the reason why a statement does not make sense, we stand within the first six teams (93.7%) among 27 participants with very competitive results. Our result for last subtask of generating reason against the nonsense statement shows many potentials for future researches as we applied the most powerful generative model of language (GPT-2) with 6.1732 BLEU score among first four teams.