Abstract
Machine reading comprehension question answering (MRC-QA) is the task of understanding the context of a given passage to find a correct answer within it. A passage is composed of several sentences; therefore, the length of the input sentence becomes longer, leading to diminished performance. In this article, we propose S3-NET, which adds sentence-based encoding to solve this problem. S3-NET, which is based on a simple recurrent unit architecture, is a deep learning model that solves the MRC-QA by applying matching network to sentence-level encoding. In addition, S3-NET utilizes self-matching networks to compute attention weight for its own recurrent neural network sequences. We perform MRC-QA for the SQuAD dataset of English and MindsMRC dataset of Korean. The experimental results show that for SQuAD, the S3-NET model proposed in this article produces 71.91% and 74.12% exact match and 81.02% and 82.34% F1 in single and ensemble models, respectively, and for MindsMRC, our model achieves 69.43% and 71.28% exact match and 81.53% and 82.77% F1 in single and ensemble models, respectively.
- Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Bengio. 2014. Neural machine translation by jointly learning to align and translate. arXiv:1409.473.Google Scholar
- Danqi Chen, Adam Fisch, Jason Weston, and Antoine Bordes. 2017. Reading Wikipedia to answer open-domain questions. arXiv:1704.00051.Google Scholar
- Zheqian Chen, Rongqin Yang, Bin Cao, Zhou Zhao, Deng Cai, and Xiaofei He. 2017. Smarnet: Teaching machines to read and comprehend like human. arXiv:1710.02772.Google Scholar
- Kyunghyun Cho, Bart Van Merriënboer, Caglar Gulcehre, Dzmitry Bahdanau, Fethi Bougares, Holger Schwenk, and Yoshua Bengio. 2014. Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv:1406.1078.Google Scholar
- Junyoung Chung, Caglar Gulcehre, KyungHyun Cho, and Yoshua Bengio. 2014. Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv:1412.3555.Google Scholar
- Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv:1810.04805.Google Scholar
- Felix Hill, Antoine Bordes, Sumit Chopra, and Jason Weston. 2015. The Goldilocks principle: Reading children’s books with explicit memory representations. arXiv:1511.02301.Google Scholar
- Minghao Hu, Yuxing Peng, Zhen Huang, Xipeng Qiu, Furu Wei, and Ming Zhou. 2017. Reinforced mnemonic reader for machine reading comprehension. arXiv:1705.02798.Google Scholar
- Yoon Kim. 2014. Convolutional neural networks for sentence classification. arXiv:1408.5882.Google Scholar
- Diederik P. Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv:1412.6980.Google Scholar
- Rupesh Kumar Srivastava, Klaus Greff, and Jürgen Schmidhuber. 2015. Highway networks. arxiv:cs.LG/1505.00387.Google Scholar
- Tao Lei and Yu Zhang. 2017. Training RNNs as fast as CNNs. arXiv:1709.02755.Google Scholar
- Tri Nguyen, Mir Rosenberg, Xia Song, Jianfeng Gao, Saurabh Tiwary, Rangan Majumder, and Li Deng. 2016. MS MARCO: A human generated machine reading comprehension dataset. arXiv:1611.09268.Google Scholar
- Cheoneum Park and Changki Lee. 2017. Coreference resolution using hierarchical pointer networks. KIISE Transaction on Computing Practices 23, 9 (2017), 542–549.Google ScholarCross Ref
- Cheoneum Park, Changki Lee, Lynn Hong, Yigyu Hwang, Taejoon Yoo, Jaeyong Jang, Yunki Hong, Kyung-Hoon Bae, and Hyun-Ki Kim. 2019. S-Net: Machine reading comprehension with SRU-based self-matching network. ETRI Journal 41, 3 (2019), 371–382.Google ScholarCross Ref
- Jeffrey Pennington, Richard Socher, and Christopher Manning. 2014. Glove: Global vectors for word representation. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP’14). 1532–1543.Google ScholarCross Ref
- Matthew E. Peters, Mark Neumann, Mohit Iyyer, Matt Gardner, Christopher Clark, Kenton Lee, and Luke Zettlemoyer. 2018. Deep contextualized word representations. arXiv:1802.05365.Google Scholar
- Pranav Rajpurkar, Jian Zhang, Konstantin Lopyrev, and Percy Liang. 2016. Squad: 100,000+ questions for machine comprehension of text. arXiv:1606.05250.Google Scholar
- Minjoon Seo, Aniruddha Kembhavi, Ali Farhadi, and Hannaneh Hajishirzi. 2016. Bidirectional attention flow for machine comprehension. arXiv:1611.01603.Google Scholar
- Yelong Shen, Po-Sen Huang, Jianfeng Gao, and Weizhu Chen. 2017. ReasoNet: Learning to stop reading in machine comprehension. In Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, New York, NY, 1047–1055.Google ScholarDigital Library
- Oriol Vinyals, Meire Fortunato, and Navdeep Jaitly. 2015. Pointer networks. In Advances in Neural Information Processing Systems. 2692–2700.Google Scholar
- Wenhui Wang, Nan Yang, Furu Wei, Baobao Chang, and Ming Zhou. 2017. Gated self-matching networks for reading comprehension and question answering. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Vol. 1. 189–198.Google ScholarCross Ref
- Dirk Weissenborn, Georg Wiese, and Laura Seiffe. 2017. Making neural QA as simple as possible but not simpler. arXiv:1703.04816.Google Scholar
Index Terms
- S3-NET: SRU-Based Sentence and Self-Matching Networks for Machine Reading Comprehension
Recommendations
Semantic matching in machine reading comprehension: An empirical study
AbstractMachine reading comprehension (MRC) is a challenging task in the field of artificial intelligence. Most existing MRC works contain a semantic matching module, either explicitly or intrinsically, to determine whether a piece of context ...
Highlights- We reveal the importance of semantic matching in Machine Reading Comprehension.
Constructing Arabic Reading Comprehension Datasets: Arabic WikiReading and KaifLematha
AbstractNeural machine reading comprehension models have gained immense popularity over the last decade given the availability of large-scale English datasets. A key limiting factor for neural model development and investigations of the Arabic language is ...
A Hereditary Attentive Template-based Approach for Complex Knowledge Base Question Answering Systems
AbstractKnowledge Base Question Answering systems (KBQA) aim to find answers to natural language questions over a knowledge base. This work presents a template matching approach for Complex KBQA systems (C-KBQA) using the combination of Semantic Parsing ...
Highlights- Knowledge base question answering systems struggle to deal with complex questions.
- A template matching approach for complex question answering.
- A Hereditary Attention that inherits the information in a bottom-up way.
- ...
Comments