NLP-IIS@UT at SemEval-2021 Task 4: Machine Reading Comprehension using the Long Document Transformer

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%).

[1]  Quoc V. Le,et al.  Distributed Representations of Sentences and Documents , 2014, ICML.

[2]  Sebastian Riedel,et al.  Constructing Datasets for Multi-hop Reading Comprehension Across Documents , 2017, TACL.

[3]  Hossein Amirkhani,et al.  A Survey on Machine Reading Comprehension Systems , 2020, Natural Language Engineering.

[4]  Jian Zhang,et al.  SQuAD: 100,000+ Questions for Machine Comprehension of Text , 2016, EMNLP.

[5]  Jeffrey Pennington,et al.  GloVe: Global Vectors for Word Representation , 2014, EMNLP.

[6]  Mark A. Changizi Economically organized hierarchies in WordNet and the Oxford English Dictionary , 2008, Cognitive Systems Research.

[7]  Sebastian Ruder,et al.  Universal Language Model Fine-tuning for Text Classification , 2018, ACL.

[8]  Luke S. Zettlemoyer,et al.  Deep Contextualized Word Representations , 2018, NAACL.

[9]  Chenguang Zhu,et al.  SDNet: Contextualized Attention-based Deep Network for Conversational Question Answering , 2018, ArXiv.

[10]  Zhiyuan Liu,et al.  Topical Word Embeddings , 2015, AAAI.

[11]  Ming-Wei Chang,et al.  BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding , 2019, NAACL.

[12]  Quan Liu,et al.  PINGAN Omini-Sinitic at SemEval-2021 Task 4:Reading Comprehension of Abstract Meaning , 2021, SEMEVAL.

[13]  Agnieszka Mykowiecka,et al.  Natural-Language Generation - An Overview , 1991, Int. J. Man Mach. Stud..

[14]  Jonathan Pilault,et al.  Conditionally Adaptive Multi-Task Learning: Improving Transfer Learning in NLP Using Fewer Parameters & Less Data , 2020, ArXiv.

[15]  Jeffrey Dean,et al.  Distributed Representations of Words and Phrases and their Compositionality , 2013, NIPS.

[16]  Arman Cohan,et al.  Longformer: The Long-Document Transformer , 2020, ArXiv.