融合句法指导与字符注意力机制的案情阅读理解方法

doi:10.11772/j.issn.1001-9081.2020101568

计算机应用 ›› 2021, Vol. 41 ›› Issue (8): 2427-2431.DOI: 10.11772/j.issn.1001-9081.2020101568

所属专题：第八届CCF大数据学术会议（CCF Bigdata 2020）

• 第八届CCF大数据学术会议 • 上一篇下一篇

融合句法指导与字符注意力机制的案情阅读理解方法

何正海^1,2, 线岩团^1,2, 王蒙^1,2, 余正涛^1,2

1. 昆明理工大学信息工程与自动化学院, 昆明 650504;
2. 云南省人工智能重点实验室(昆明理工大学), 昆明 650504

收稿日期:2020-07-15 修回日期:2020-09-18 发布日期:2021-01-27 出版日期:2021-08-10
通讯作者: 线岩团
作者简介:何正海(1991-),男,甘肃兰州人,硕士研究生,CCF会员,主要研究方向:自然语言处理、信息检索;线岩团(1981-),男,云南昆明人,副教授,博士研究生,CCF会员,主要研究方向:自然语言处理、信息抽取;王蒙(1981-),男,云南昆明人,副教授,博士,主要研究方向:计算机视觉、图像处理、机器学习、语音识别;余正涛(1970-),男,云南昆明人,教授,博士,CCF会员,主要研究方向:自然语言处理、信息检索、机器翻译、机器学习、智能系统、决策分析。
基金资助:
国家重点研发计划项目（2018YFC0830100）；云南省基础研究专项（202001AT070046）。

Case reading comprehension method combining syntactic guidance and character attention mechanism

HE Zhenghai^1,2, XIAN Yantuan^1,2, WANG Meng^1,2, YU Zhengtao^1,2

1. Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming Yunnan 650504, China;
2. Yunnan Key Laboratory of Artificial Intelligence(Kunming University of Science and Technology), Kunming Yunnan 650504, China

Received:2020-07-15 Revised:2020-09-18 Online:2021-01-27 Published:2021-08-10
Supported by:
This work is partially supported by the National Key Research and Development Program of China (2018YFC0830100), the Special Project of Basic Research of Yunnan Province (202001AT070046).

摘要/Abstract

摘要： 案情阅读理解是机器阅读理解在司法领域的具体应用。案情阅读理解通过计算机阅读裁判文书，并回答相关问题，是司法智能化的重要应用之一。当前机器阅读理解的主流方法是采用深度学习模型对文本词语进行编码，并由此获得文本的向量表示。模型建立的核心问题是如何获得文本的语义表示，以及问题与上下文的匹配。考虑到句法信息有助于模型学习句子主干信息，以及中文字符具有潜在的语义信息，提出了融合句法指导与字符注意力机制的案情阅读理解方法。通过融合句法信息及中文字符信息，提升模型对案情文本的编码能力。在法研杯2019阅读理解数据集上的实验结果表明，所提出的方法与基线模型相比EM值提升了0.816，F1值提升了1.809%。

关键词: 阅读理解, 裁判文书, 字符注意力, 句法指导注意力, 深度学习

Abstract: Case reading comprehension is the specific application of machine reading comprehension in judicial field. Case reading comprehension is one of the important applications of judicial intelligence, which reads the judgment documents by computer and answers the related questions. At present, the mainstream method of machine reading comprehension is to use deep learning model to encode the text words and obtain vector representation of the text. The core problem of model construction is how to obtain the semantic representation of the text and how to match the questions with the context. Considering that syntactic information is helpful for model learning the sentence skeleton information and Chinese characters have potential semantic information, a case reading comprehension method that integrates syntactic guidance and character attention mechanism was proposed. By fusing the syntactic information and Chinese character information, the coding ability of the model for the case text was improved. Experimental results on the reading comprehension dataset of Law Research Cup 2019 show that compared with the baseline model, the proposed method has the Exact Match (EM) value increased by 0.816 and the F1 value improved by 1.809%.

Key words: reading comprehension, judgment document, character attention, syntactically guided attention, deep learning

中图分类号:

TP391

何正海, 线岩团, 王蒙, 余正涛. 融合句法指导与字符注意力机制的案情阅读理解方法[J]. 计算机应用, 2021, 41(8): 2427-2431.

HE Zhenghai, XIAN Yantuan, WANG Meng, YU Zhengtao. Case reading comprehension method combining syntactic guidance and character attention mechanism[J]. Journal of Computer Applications, 2021, 41(8): 2427-2431.

参考文献

[1] KIM Y. Convolutional neural networks for sentence classification[C]//Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing. Stroudsburg,PA:Association for Computational Linguistics,2014:1746-1751.
[2] HOCHREITER S,SCHMIDHUBER J. Long short-term memory[J]. Neural Computation,1997,9(8):1735-1780.
[3] VASWANI A,SHAZEER N,PARMAR N,et al. Attention is all you need[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems. Red Hook,NY:Curran Associates Inc.,2017:6000-6010.
[4] SEO M, KEMBHAVI A, FARHADI A, et al. Bi-directional attention flow for machine comprehension[EB/OL]. (2018-06-21)[2020-05-15]. https://arxiv.org/pdf/1611.01603.pdf.
[5] HUANG H Y,ZHU C G,SHEN Y L,et al. FusionNet:fusing via fully-aware attention with application to machine comprehension[EB/OL]. (2018-02-04)[2020-05-15]. https://arxiv.org/pdf/1711.07341.pdf.
[6] YU A W,DOHAN D,LUONG M T,et al. QANet:combining local convolution with global self-attention for reading comprehension[EB/OL]. (2018-04-23)[2020-05-15]. https://arxiv.org/pdf/1804.09541.pdf.
[7] SUN F, LI L Y, QIU X P, et al. U-Net:machine reading comprehension with unanswerable questions[EB/OL]. (2018-10-12)[2020-06-15]. https://arxiv.org/pdf/1810.06638.pdf.
[8] WANG W, YAN M, WU C. Multi-granularity hierarchical attention fusion networks for reading comprehension and question answering[C]//Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics. Stroudsburg, PA:Association for Computational Linguistics,2018:1705-1714.
[9] LIU X D,SHEN Y L,DUH K,et al. Stochastic answer networks for machine reading comprehension[C]//Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics. Stroudsburg, PA:Association for Computational Linguistics, 2018:1694-1704.
[10] RAJPURKAR P, ZHANG J, LOPYREV K, et al. SQuAD:100,000+ questions for machine comprehension of text[C]//Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing. Stroudsburg,PA:Association for Computational Linguistics,2016:2383-2392.
[11] XIONG C M,ZHONG V,SOCHER R. DCN+:mixed objective and deep residual coattention for question answering[EB/OL]. (2017-11-10)[2020-05-15]. https://arxiv.org/pdf/1711.00106.pdf.
[12] RAJPURKAR P,JIA R,LIANG P. Know what you don't know:unanswerable questions for SQuAD[C]//Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics. Stroudsburg, PA:Association for Computational Linguistics, 2018:784-789.
[13] McCANN B,BRADBURY J,XIONG C M,et al. Learned in translation:contextualized word vectors[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems. Red Hook,NY:Curran Associates Inc.,2017:6297-6308.
[14] JI J S,WANG Q L,TOUTANOVA K,et al. A nested attention neural hybrid model for grammatical error correction[C]//Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics. Stroudsburg, PA:Association for Computational Linguistics,2017:753-762.
[15] LIU R,HU J J,WEI W,et al. Structural embedding of syntactic trees for machine comprehension[C]//Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing. Stroudsburg, PA:Association for Computational Linguistics, 2017:815-824.
[16] WANG X Y,XU G L,ZHANG J Y,et al. Syntax-directed hybrid attention network for aspect-level sentiment analysis[J]. IEEE Access,2019,7:5014-5025.
[17] ZHANG Z S,WU Y W,ZHOU J R,et al. SG-Net:syntax-guided machine reading comprehension[C]//Proceedings of the 34th AAAI Conference on Artificial Intelligence. Palo Alto,CA:AAAI Press,2020:9636-9643.
[18] ZHANG X,ZHAO J B,LeCUN Y. Character-level convolutional networks for text classification[C]//Proceedings of the 28th Conference on Neural Information Processing Systems. Cambridge:MIT Press,2015:649-657.
[19] BOJANOWSKI P,GRAVE E,JOULIN A,et al. Enriching word vectors with subword information[J]. Transactions of the Association for Computational Linguistics,2017,5:135-146.
[20] PASZKE A, GROSS S, CHINTALA S, et al. Automatic differentiation in PyTorch[EB/OL].[2020-06-15]. https://openreview.net/pdf/25b8eee6c373d48b84e5e9c6e10e7cbbbce4ac73.pdf.

融合句法指导与字符注意力机制的案情阅读理解方法

Case reading comprehension method combining syntactic guidance and character attention mechanism

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	潘烨新, 杨哲. 基于多级特征双向融合的小目标检测优化模型[J]. 《计算机应用》唯一官方网站, 2024, 44(9): 2871-2877.
[2]	秦璟, 秦志光, 李发礼, 彭悦恒. 基于概率稀疏自注意力神经网络的重性抑郁疾患诊断[J]. 《计算机应用》唯一官方网站, 2024, 44(9): 2970-2974.
[3]	王熙源, 张战成, 徐少康, 张宝成, 罗晓清, 胡伏原. 面向手术导航3D/2D配准的无监督跨域迁移网络[J]. 《计算机应用》唯一官方网站, 2024, 44(9): 2911-2918.
[4]	黄云川, 江永全, 黄骏涛, 杨燕. 基于元图同构网络的分子毒性预测[J]. 《计算机应用》唯一官方网站, 2024, 44(9): 2964-2969.
[5]	李顺勇, 李师毅, 胥瑞, 赵兴旺. 基于自注意力融合的不完整多视图聚类算法[J]. 《计算机应用》唯一官方网站, 2024, 44(9): 2696-2703.
[6]	刘禹含, 吉根林, 张红苹. 基于骨架图与混合注意力的视频行人异常检测方法[J]. 《计算机应用》唯一官方网站, 2024, 44(8): 2551-2557.
[7]	顾焰杰, 张英俊, 刘晓倩, 周围, 孙威. 基于时空多图融合的交通流量预测[J]. 《计算机应用》唯一官方网站, 2024, 44(8): 2618-2625.
[8]	石乾宏, 杨燕, 江永全, 欧阳小草, 范武波, 陈强, 姜涛, 李媛. 面向空气质量预测的多粒度突变拟合网络[J]. 《计算机应用》唯一官方网站, 2024, 44(8): 2643-2650.
[9]	赵亦群, 张志禹, 董雪. 基于密集残差物理信息神经网络的各向异性旅行时计算方法[J]. 《计算机应用》唯一官方网站, 2024, 44(7): 2310-2318.
[10]	徐松, 张文博, 王一帆. 基于时空信息的轻量视频显著性目标检测网络[J]. 《计算机应用》唯一官方网站, 2024, 44(7): 2192-2199.
[11]	孙逊, 冯睿锋, 陈彦如. 基于深度与实例分割融合的单目3D目标检测方法[J]. 《计算机应用》唯一官方网站, 2024, 44(7): 2208-2215.
[12]	刘青, 陈艳平, 邹安琪, 黄瑞章, 秦永彬. 面向机器阅读理解的边界感知方法[J]. 《计算机应用》唯一官方网站, 2024, 44(7): 2004-2010.
[13]	吴筝, 程志友, 汪真天, 汪传建, 王胜, 许辉. 基于深度学习的患者麻醉复苏过程中的头部运动幅度分类方法[J]. 《计算机应用》唯一官方网站, 2024, 44(7): 2258-2263.
[14]	李欢欢, 黄添强, 丁雪梅, 罗海峰, 黄丽清. 基于多尺度时空图卷积网络的交通出行需求预测[J]. 《计算机应用》唯一官方网站, 2024, 44(7): 2065-2072.
[15]	张郅, 李欣, 叶乃夫, 胡凯茜. 基于暗知识保护的模型窃取防御技术DKP[J]. 《计算机应用》唯一官方网站, 2024, 44(7): 2080-2086.