基于动态网络的简答题答案标注方法
Answer Annotation for Short-Answer Questions Based on Dynamic Network
DOI: 10.12677/CSA.2022.129225, PDF,    科研立项经费支持
作者: 洪旭东, 严 梅*, 莫媛媛：安徽工业大学计算机科学与技术学院，安徽 马鞍山
关键词: 阅读理解；问答；答案标注；动态网络；关注机制；Reading Comprehension； Question Answering； Answer Pointing； Dynamic Network； Attention Mechanism
摘要: 阅读理解问答是当前自然语言处理的研究热点之一。针对阅读理解问答中的简答题，由于其答案往往有多个、分布在阅读材料的不同位置，现有方法大多难以有效获取。本论文面向简答题的答案标注方法开展研究，将简答题答案标注问题看作是序列标注问题，考虑到问句焦点词对于寻找答案具有重要作用，提出基于动态网络的简答题答案标注方法，实现了简答题答案的端到端标注，实验表明提出的方法在F1和EM值上效果都有所提升。
Abstract: Reading comprehension style question answering is one of the current research hotspots in natural language processing. For the short-answer questions, since the answers are often multiple and distributed in different positions of the reading passages, most of the existing methods are difficult to obtain effectively. This paper studies the answer labeling method for short-answer questions, regards the short-answer question answer labeling problem as a sequence labeling problem, and considers that the focus words of questions play an important role in finding answers, and proposes a dynamic network-based short-answer question answer labeling method. End-to-end annotation of short-answer questions’ answers, experiments show that the proposed method improves both F1 and EM values.
文章引用：洪旭东, 严梅, 莫媛媛. 基于动态网络的简答题答案标注方法[J]. 计算机科学与应用, 2022, 12(9): 2217-2224. https://doi.org/10.12677/CSA.2022.129225

参考文献

[1] Seo, M., Kembhavi, A., Farhadi, A., et al. (2016) Bidirectional Attention Flow for Machine Comprehension. Proceed-ings of the International Conference on Learning Representations, Toulon, 24-26 April 2017, 1-13.
[2] Pennington, J., Socher, R., Manning, C.D., et al. (2014) Glove: Global Vectors for Word Representation. Proceedings of the 2014 Con-ference on Empirical Methods in Natural Language Processing, Doha, October 2014, 1532-1543. [Google Scholar] [CrossRef] 
[3] Kim, Y. (2014) Convolutional Neural Networks for Sentence Classifica-tion. Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, Doha, October 2014, 1746-1751. [Google Scholar] [CrossRef] 
[4] Srivastava, R.K., Greff, K., Schmidhuber, J., et al. (2015) Highway Networks.
[5] Chen, D.Q., Fisch, A., Weston, J., et al. (2017) Reading Wikipedia to Answer Open-Domain Questions. Proceedings of the 55th Annual Meeting of the Association for Computational Linguistic, Volume 1, 1870-1879. [Google Scholar] [CrossRef] 
[6] Weissenborn, D., Wiese, G., Seiffe, L., et al. (2016) Making Neural QA as Simple as Possible but Not Simpler. Proceedings of the 21st Conference on Computational Natural Language Learning, Vancouver, 3-4 August 2017, 271-280. [Google Scholar] [CrossRef] 
[7] Wang, H.H. and Jiang, J. (2016) Machine Comprehension Using Match-LSTM and Answer Pointer.
[8] Hochreiter, S. and Schmidhuber, J. (1997) Long Short-Term Memory. Neural Computation, 9, 1735-1780. [Google Scholar] [CrossRef] [PubMed]
[9] Choi, E., Hewlett, D., Uszkoreit, J., et al. (2017) Coarse-to-Fine Question Answering for Long Documents. Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, Volume 1, 209-220. [Google Scholar] [CrossRef] 
[10] Cho, K., Van Merrienboe, B., Gulcehre, C., et al. (2016) Learning Phrase Representations Using RNN Encoder-Decoder for Statistical Machine Translation. Proceedings of the 2014 Con-ference on Empirical Methods in Natural Language Processing, Doha, 25-29 October 2014, 1724-1734. [Google Scholar] [CrossRef] 
[11] Wang, W.H., Yang, N., Wei, F.R., et al. (2017) Gated Self-Matching Networks for Reading Comprehension and Question Answering. Proceedings of the 55th Annual Meeting of the Associ-ation for Computational Linguistics, Volume 1, 189-198. [Google Scholar] [CrossRef] 
[12] Huang, H.-Y., Zhu, C.G., Shen, Y.L., et al. (2017) FusionNet: Fusing via Fully-Aware Attention with Application to Machine Com-prehension. Proceedings of the International Conference on Learning Representations, Vancouver, 30 April-3 May 2018, 1-20.
[13] Tay, Y., Tuan, L.A. and Hui, S.C. (2018) Multi-Range Reasoning for Machine Comprehension.
[14] Xiong, C.M., Zhong, V. and Socher, R. (2016) Dynamic Coattention Networks for Question Answering. International Confer-ence on Learning Representations 2017, Toulon, 24-26 April 2017, 1-14.
[15] Cui, Y., Chen, Z., Wei, S., et al. (2017) Attention-over-Attention Neural Networks for Reading Comprehension. Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, Volume 1, 593-602. [Google Scholar] [CrossRef] 
[16] Wang, Z.G., Mi, H.T., Hamza, W. and Florian, R. (2016) Mul-ti-Perspective Context Matching for Machine Comprehension.
[17] Vinyals, O., Fortunato, M. and Jaitly, N. (2015) Pointer Networks. Proceedings of the Conference on Advances in Neural Information Processing Systems, Volume 2, 2692-2700.
[18] Rajpurkar, P., Zhang, J., Lopyrev, K., et al. (2016) SQuAD: 100,000+ Questions for Machine Com-prehension of Text. Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, Austin, 1-5 November 2016, 2383-2392. [Google Scholar] [CrossRef] 
[19] Kocisky, T., Schwarz, J., Blunsom, P., et al. (2017) The NarrativeQA Reading Comprehension Challenge.
[20] Nguyen, T., Rosenberg, M., Song, X., et al. (2016) MS MARCO: A Human Generated Machine Reading Comprehension Dataset.