ZJUKLAB at SemEval-2021 Task 4: Negative Augmentation with Language Model for Reading Comprehension of Abstract Meaning
This is an incremental improvement for natural language processing researchers focused on abstract meaning comprehension in reading tasks.
The paper tackled the SemEval-2021 Task 4 on Reading Comprehension of Abstract Meaning by proposing negative augmentation with a language model, achieving 4th rank with accuracies of 87.9% and 92.8% on two subtasks.
This paper presents our systems for the three Subtasks of SemEval Task4: Reading Comprehension of Abstract Meaning (ReCAM). We explain the algorithms used to learn our models and the process of tuning the algorithms and selecting the best model. Inspired by the similarity of the ReCAM task and the language pre-training, we propose a simple yet effective technology, namely, negative augmentation with language model. Evaluation results demonstrate the effectiveness of our proposed approach. Our models achieve the 4th rank on both official test sets of Subtask 1 and Subtask 2 with an accuracy of 87.9% and an accuracy of 92.8%, respectively. We further conduct comprehensive model analysis and observe interesting error cases, which may promote future researches.