IIE-NLP-NUT at SemEval-2020 Task 4: Guiding PLM with Prompt Template Reconstruction Strategy for ComVE
This work addresses commonsense reasoning challenges in NLP, but it is incremental as it adapts existing methods to a specific benchmark.
The paper tackled commonsense validation and explanation tasks by proposing a prompt template reconstruction strategy to guide pre-trained language models, achieving accuracies of 96.4% and 94.3% on two subtasks, securing third place in the competition.
This paper introduces our systems for the first two subtasks of SemEval Task4: Commonsense Validation and Explanation. To clarify the intention for judgment and inject contrastive information for selection, we propose the input reconstruction strategy with prompt templates. Specifically, we formalize the subtasks into the multiple-choice question answering format and construct the input with the prompt templates, then, the final prediction of question answering is considered as the result of subtasks. Experimental results show that our approaches achieve significant performance compared with the baseline systems. Our approaches secure the third rank on both official test sets of the first two subtasks with an accuracy of 96.4 and an accuracy of 94.3 respectively.