NLP-IIS@UT at SemEval-2021 Task 4: Machine Reading Comprehension using the Long Document Transformer
This is an incremental improvement for researchers in NLP, specifically addressing performance in reading comprehension tasks with long documents.
The paper tackled the problem of machine reading comprehension with lengthy contexts by using the Longformer model, improving accuracy from 23.01% and 22.95% to 70.30% and 64.38% on subtasks compared to baselines.
This paper presents a technical report of our submission to the 4th task of SemEval-2021, titled: Reading Comprehension of Abstract Meaning. In this task, we want to predict the correct answer based on a question given a context. Usually, contexts are very lengthy and require a large receptive field from the model. Thus, common contextualized language models like BERT miss fine representation and performance due to the limited capacity of the input tokens. To tackle this problem, we used the Longformer model to better process the sequences. Furthermore, we utilized the method proposed in the Longformer benchmark on Wikihop dataset which improved the accuracy on our task data from 23.01% and 22.95% achieved by the baselines for subtask 1 and 2, respectively, to 70.30% and 64.38%.