机器阅读理解综述
A Review of Machine Reading Comprehension

DOI: 10.12677/CSA.2020.1012261, PP. 2457-2465

Keywords: 机器阅读理解，深度学习，词向量，自然语言处理
Machine Reading Comprehension, Deep Learning, Word Vector, Natural Language Processing

Full-Text   Cite this paper   Add to My Lib

Abstract:

机器阅读理解是为了让机器能够真正理解人类语言，它是人工智能发展过程中不可或缺的步骤。由于自然语言的复杂性和多样性导致全面理解自然语言是智能化领域的难点问题之一。本文介绍了机器阅读理解相关的技术方法，主要分为基于规则的方法、基于机器学习的方法和基于深度学习的方法，并分类对机器阅读理解领域的相关代表性工作进行了详细的总结。随着深度学习在多个领域取得成果能够，本文重点介绍了基于深度学习的机器阅读理解方法。最后本文对机器阅读理解未来发展趋势进行展望。
Machine reading comprehension is to make the machine truly understand human language. Machine reading comprehension is an indispensable step in the development of artificial intelligence. Due to the complexity and diversity of the natural language, comprehensive understanding of the language is one of the difficult problems in the field of the intelligence. This paper introduces the related technologies and methods of machine reading comprehension, which are mainly divided into rule-based, machine learning-based and deep learning-based. We summarize the relevant representative work in detail. With the achievements of deep learning in many fields, this paper focuses on the machine reading comprehension method based on deep learning. Finally, the future development trend of machine reading comprehension is prospected.

References

[1]	Schank, R.C. and Abelson, R.P. (1978) Scripts, Plans, Goals, and Understanding: An Inquiry into Human Knowledge Structures. Language, 54, 779. https://doi.org/10.2307/412850
[2]	Berant, J., et al. (2013) Semantic Parsing on Freebase from Question-Answer Pairs. Proceedings of the 2013 Conference on EMNLP, Washington DC, July 2013, 1533-1544.
[3]	Hermann, K.M., et al. (2015) Teaching Machines to Read and Comprehend.
[4]	Wg, L. (1977) The Process of Question and Answering. PhD Thesis, Yale University, New Haven.
[5]	Hirschman, L., et al. (1999) Deep Read: A Reading Comprehension System. Proceedings of the 37th Conference on ACL, Maryland, June 1999, 325-332. https://doi.org/10.3115/1034678.1034731
[6]	Richardson, et al. (2013) MCTest: A Challenge Dataset for the Open-Domain Machine Comprehension of Tex. In: Proceedings of the 2013 Conference on Empirical Methods in Natu-ral Language Processing, Association for Computational Linguistics, Stroudsburg, 193-203.
[7]	Narasimhan, K. and Barzilay, R. (2015) Machine Comprehension with Discourse Relations. Meeting of the Association for Computational Linguistics & the International Joint Conference on Natural Language Processing, Volume 1, 1253-1262. https://doi.org/10.3115/v1/P15-1121
[8]	Sachan, M., et al. (2015) Learning Answer-Entailing Structures for Ma-chine Comprehension. Meeting of the Association for Computational Linguistics & the International Joint Conference on Natural Language Processing, Volume 1, 239-249. https://doi.org/10.3115/v1/P15-1024
[9]	Wang, H., et al. (2015) Machine Comprehension with Syntax, Frames, and Semantics. Proceedings of the IJCNLP, Beijing, July 2015, 700-706.
[10]	Rajpurkar, P., et al. (2016) SQuAD: 100,000+ Questions for Machine Comprehension of Text. Proceed-ings of the 2016 Conference on Empirical Methods in Natural Language Processing, Austin, November 2016, 2383-2392. https://doi.org/10.18653/v1/D16-1264
[11]	Joshi, M., et al. (2017) TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension. Proceedings of the 55th Conference on ACL, Vancouver, July 2017, 1601-1611. https://doi.org/10.18653/v1/P17-1147
[12]	Trischler, A., et al. (2017) NewsQA: A Machine Compre-hension Dataset. Proceedings of the 2nd Workshop on Representation Learning for NLP, Vancouver, August 2017, 191-200. https://doi.org/10.18653/v1/W17-2623
[13]	Dunn, M., et al. (2017) SearchQA: A New Q&A Dataset Augmented with Context from a Search Engine.
[14]	Shao, C.C., et al. (2018) DRCD: A Chinese Machine Reading Comprehension Dataset.
[15]	Cui, Y., et al. (2018) A Span-Extraction Dataset for Chinese Machine Reading Compre-hension. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th Inter-national Joint Conference on Natural Language Processing (EMNLP-IJCNLP), Hong Kong, November 2019, 5883-5889. https://doi.org/10.18653/v1/D19-1600
[16]	Duan, X., et al. (2019) CJRC: A Reliable Human-Annotated Bench-mark DataSet for Chinese Judicial Reading Comprehension. In: China National Conference on Chinese Computational Linguistics, Springer, Cham, 439-451. https://doi.org/10.1007/978-3-030-32381-3_36
[17]	Lai, G., et al. (2017) RACE: Large-Scale Reading Compre-hension Dataset from Examinations. Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, Copenhagen, September 2017, 785-794. https://doi.org/10.18653/v1/D17-1082
[18]	Hill, F., et al. (2015) The Goldilocks Principle: Reading Children’s Books with Explicit Memory Representations.
[19]	Cui, Y., et al. (2016) Consensus Attention-Based Neural Networks for Chinese Reading Comprehension. Proceedings of COLING 2016, the 26th International Conference on Computa-tional Linguistics: Technical Papers, Osaka, December 2016, 1777-1786.
[20]	Ko？isky, T., et al. (2017) The Narra-tiveQA Reading Comprehension Challenge. Transactions of the Association for Computational Linguistics, 6, 317-328. https://doi.org/10.1162/tacl_a_00023
[21]	Nguyen, T., et al. (2016) MS MARCO: A Human Generated Machine Reading Comprehension Dataset.
[22]	He, W., et al. (2017) DuReader: a Chinese Machine Reading Comprehension Dataset from Real-world Applications. Proceedings of the Workshop on Machine Reading for Question Answering, Melbourne, July 2018, 37-46. https://doi.org/10.18653/v1/W18-2605
[23]	Yang, Z., et al. (2018) HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering. Proceedings of the 2018 Conference on Empirical Methods in Natural Language Pro-cessing, Brussels, October-November 2018, 2369-2380. https://doi.org/10.18653/v1/D18-1259
[24]	Riloff, E. and Thelen, M. (2000) A Rule-Based Question Answering System for Reading Comprehension Tests. Proceedings of the 2000 ANLP/NAACL Workshop on Reading Comprehension Tests as Evaluation for Computer-Based Language Under-standing Systems, Volume 6, 13-19. https://doi.org/10.3115/1117595.1117598
[25]	Poon, H., et al. (2010) Ma-chine Reading at the University of Washington. NAACL HLT First International Workshop on Formalisms & Method-ology for Learning by Reading, Los Angeles, June 2010, 87-95.
[26]	Berant, J., et al. (2014) Modeling Biological Pro-cesses for Reading Comprehension. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), Association for Computational Linguistics, Stroudsburg, 1499-1510. https://doi.org/10.3115/v1/D14-1159
[27]	Chen, D., Bolton, J. and Manning, C.D. (2016) A Thorough Examina-tion of the CNN/Daily Mail Reading Comprehension Task. Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, Volume 1, 2358-2367. https://doi.org/10.18653/v1/P16-1223
[28]	Wang, S. and Jiang, J. (2016) Machine Comprehension Using Match-LSTM and Answer Pointer.
[29]	Chen, D., et al. (2017) Read-ing Wikipedia to Answer Open-Domain Questions. Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, Volume 1, 1870-1879. https://doi.org/10.18653/v1/P17-1171
[30]	Wang, W., et al. (2017) Gated Self-Matching Networks for Reading Comprehension and Question Answering. Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, Volume 1, 189-198. https://doi.org/10.18653/v1/P17-1018
[31]	Yu, A.W., et al. (2018) QANet: Combining Local Convolution with Global Self-Attention for Reading Comprehension.
[32]	Rajpurkar, P., Jia, R. and Liang, P. (2018) Know What You Don’t Know: Unanswerable Questions for SQuAD. Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, Volume 2, 784-789. https://doi.org/10.18653/v1/P18-2124
[33]	Yang, Z., et al. (2019) XLNet: Generalized Autoregressive Pretraining for Language Understanding.
[34]	Mikolov, T., et al. (2013) Efficient Estimation of Word Representations in Vector Space.
[35]	Pennington, J., Socher, R. and Manning, C. (2014) Glove: Global Vectors for Word Representation. Con-ference on Empirical Methods in Natural Language Processing, Doha, October 2014, 1532-1543. https://doi.org/10.3115/v1/D14-1162
[36]	Bojanowski, P., et al. (2017) Enriching Word Vectors with Subword Information. Transactions of the Association for Computational Linguistics, 5, 135-146. https://doi.org/10.1162/tacl_a_00051
[37]	Mccann, B., et al. (2017) Learned in Translation: Contextualized Word Vectors.
[38]	Peters, M., et al. (2018) Deep Contextualized Word Representations. Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1, 2227-2237. https://doi.org/10.18653/v1/N18-1202
[39]	Vaswani, A., et al. (2017) Attention Is All You Need.
[40]	Dai, Z., et al. (2019) Transformer-XL: Attentive Language Models beyond a Fixed-Length Context. Pro-ceedings of the 57th Annual Meeting of the Association for Computational Linguistics, Florence, July 2019, 2978-2988. https://doi.org/10.18653/v1/P19-1285
[41]	Williams, R. and Zipser, D. (2014) A Learning Algorithm for Continu-ally Running Fully Recurrent Neural Networks. Neural Computation, 1, 270-280. https://doi.org/10.1162/neco.1989.1.2.270
[42]	Hochreiter, S. and Schmidhuber, J. (1997) Long Short-Term Memory. Neural Computation, 9, 1735-1780. https://doi.org/10.1162/neco.1997.9.8.1735
[43]	Cho, K., et al. (2014) Learning Phrase Representations Using RNN Encoder-Decoder for Statistical Machine Translation. Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), Doha, October 2014, 1724-1734. https://doi.org/10.3115/v1/D14-1179
[44]	Lecun, Y. and Bengio, Y. (1995) Convolutional Networks for Images, Speech, and Time-Series. In: Arbib, M.A., Ed., Handbook of Brain Theory & Neural Networks, MIT Press, Boston, 255-258.
[45]	Wang, W., et al. (2017) Gated Self-Matching Networks for Reading Comprehension and Question An-swering. Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, Volume 1, 189-198. https://doi.org/10.18653/v1/P17-1018

Full-Text