基于注意力和字嵌入的中文医疗问答匹配方法

doi:10.11772/j.issn.1001-9081.2018102184

计算机应用 ›› 2019, Vol. 39 ›› Issue (6): 1639-1645.DOI: 10.11772/j.issn.1001-9081.2018102184

基于注意力和字嵌入的中文医疗问答匹配方法

陈志豪¹, 余翔¹, 刘子辰², 邱大伟², 顾本刚¹

1. 重庆邮电大学通信与信息工程学院, 重庆 400065;
2. 移动计算与新型终端北京重点实验室(中国科学院计算技术研究所), 北京 100190

收稿日期:2018-10-31 修回日期:2018-12-31 出版日期:2019-06-10 发布日期:2019-06-17
通讯作者: 陈志豪
作者简介:陈志豪(1994-),男,重庆人,硕士研究生,主要研究方向:自然语言处理、智能问答系统;余翔(1964-),男,四川成都人,正高级工程师,主要研究方向:数字通信、无线信号处理;刘子辰(1985-),男,山东临沂人,助理研究员,主要研究方向:网络通信、大数据挖掘;邱大伟(1991-),男,内蒙古赤峰市人,博士研究生,主要研究方向:模式识别、机器学习、自然语言处理;顾本刚(1992-),男,安徽淮南人,硕士研究生,主要研究方向:网络通信。
基金资助:
国家重大科技专项（2016ZX03002010-003）。

Chinese medical question answer matching method based on attention mechanism and character embedding

CHEN Zhihao¹, YU Xiang¹, LIU Zichen², QIU Dawei², GU Bengang¹

1. School of Communication and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing 400065, China;
2. Beijing Key Laboratory of Mobile Computing and Pervasive Device(Institute of Computing Technology, Chinese Academy of Sciences), Beijing 100190, China

Received:2018-10-31 Revised:2018-12-31 Online:2019-06-10 Published:2019-06-17
Supported by:
This work is partially supported by National Science and Technology Major Project (2016ZX03002010-003).

摘要/Abstract

摘要： 针对当前的分词工具在中文医疗领域无法有效切分出所有医学术语，且特征工程需消耗大量人力成本的问题，提出了一种基于注意力机制和字嵌入的多尺度卷积神经网络建模方法。该方法使用字嵌入结合多尺度卷积神经网络用以提取问题句子和答案句子不同尺度的上下文信息，并引入注意力机制来强调问题和答案句子之间的相互影响，该方法能有效学习问题句子和正确答案句子之间的语义关系。由于中文医疗领域问答匹配任务没有标准的评测数据集，因此使用公开可用的中文医疗问答数据集（cMedQA）进行评测，实验结果表明该方法优于词匹配、字匹配和双向长短时记忆神经网络（BiLSTM）建模方法，并且Top-1准确率为65.43%。

关键词: 自然语言处理, 问答对匹配, 卷积神经网络, 字嵌入, 注意力机制

Abstract: Aiming at the problems that the current word segmentation tool can not effectively distinguish all medical terms in Chinese medical field, and feature engineering has high labor cost, a multi-scale Convolutional Neural Network (CNN) modeling method based on attention mechanism and character embedding was proposed. In the proposed method, character embedding was combined with multi-scale CNN to extract context information at different scales of question and answer sentences, and attention mechanism was introduced to emphasize the interaction between question sentences and answer sentences, meanwhile the semantic relationship between the question sentence and the correct answer sentence was able to be effectively learned. Since the question and answer matching task in Chinese medical field does not have a standard evaluation dataset, the proposed method was evaluated using the publicly available Chinese Medical Question and Answer dataset (cMedQA). The experimental results show that the proposed method is superior to word matching, character matching and Bi-directional Long Short-Term Memory network (BiLSTM) modeling method, and the Top-1 accuracy is 65.43%.

Key words: natural language processing, question answer matching, Convolutional Neural Network (CNN), character embedding, attention mechanism

中图分类号:

TP183

陈志豪, 余翔, 刘子辰, 邱大伟, 顾本刚. 基于注意力和字嵌入的中文医疗问答匹配方法[J]. 计算机应用, 2019, 39(6): 1639-1645.

CHEN Zhihao, YU Xiang, LIU Zichen, QIU Dawei, GU Bengang. Chinese medical question answer matching method based on attention mechanism and character embedding[J]. Journal of Computer Applications, 2019, 39(6): 1639-1645.

参考文献

[1] FENG M W, XIANG B, GLASS M R, et al. Applying deep learning to answer selection:a study and an open task[C]//Proceedings of the 2015 IEEE Workshop on Automatic Speech Recognition and Understanding. Piscataway, NJ:IEEE, 2015:813-820.
[2] TAN M, dos SANTOS C N, XIANG B, et al. Improved representation learning for question answer matching[C]//ACL 2016:Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics. Cambridge, CA:MIT Press, 2016:464-473.
[3] QIU X P, HUANG X J. Convolutional neural tensor network architecture for community-based question answering[C]//IJCAI 2015:Proceedings of the 24th International Conference on Artificial Intelligence. Menlo Park, CA:AAAI Press, 2015:1305-1311.
[4] YIN W P, SCHVTZE H, XIANG B, et al. ABCNN:attention-based convolutional neural network for modeling sentence pairs[EB/OL].[2018-08-20]. http://cn.arxiv.org/abs/1512.05193.pdf.
[5] JAIN S, DODIYA T. Rule based architecture for medical question answering system[C]//SocProS 2012:Proceedings of the Second International Conference on Soft Computing for Problem Solving, AISC 236. Berlin:Springer, 2014:1225-1233.
[6] WANG J, MAN C T, ZHAO Y F, et al. An answer recommendation algorithm for medical community question answering systems[C]//SOLI 2016:Proceedings of the 2016 IEEE International Conference on Service Operations and Logistics, and Informatics. Piscataway, NJ:IEEE, 2016:139-144.
[7] ABACHA A B, ZWEIGENBAUM P. Medical question answering:translating medical questions into SPARQL queries[C]//Proceedings of the 2nd ACM SIGHIT International Health Informatics Symposium. New York:ACM, 2012:41-50.
[8] ABACHA A B, ZWEIGENBAUM P. MEANS:a medical question-answering system combining NLP techniques and semantic Web technologies[J]. Information Processing & Management, 2015, 51(5):570-594.
[9] LI T C, HAO Y, ZHU X Y, et al. A Chinese question answering system for specific domain[C]//WAIM 2014:Proceedings of the International Conference on Web-Age Information Management. Berlin:Springer, 2014:590-601.
[10] YIN Y S, ZHANG Y, LIU X, et al. HealthQA:a Chinese QA summary system for smart health[C]//CSH 2014:Proceedings of the 2nd International Conference on Smart Health, LNCS 8549. Cham:Springer, 2014:51-62.
[11] WANG B Y, NIU J B, MA L Q, et al. A Chinese question answering approach integrating count-based and embedding-based features[C]//Proceedings of the 2016 International Conference on Computer Processing of Oriental Languages, National CCF Conference on Natural Language Processing and Chinese Computing, LNCS 10102. Cham:Springer, 2016:934-941.
[12] HU B T, LU Z D, LI H, et al. Convolutional neural network architectures for matching natural language sentences[C]//NIPS 2014:Proceedings of the 27th International Conference on Neural Information Processing Systems. Cambridge, CA:MIT Press, 2014:2042-2050.
[13] ZHOU X Q, HU B T, CHEN Q C, et al. Answer sequence learning with neural networks for answer selection in community question answering[EB/OL].[2018-08-14]. https://arxiv.org/abs/1506.06490.pdf.
[14] TAN M, dos SANTOS C N, XIANG B, et al. LSTM-based deep learning models for non-factoid answer selection[EB/OL].[2018-08-20]. https://arxiv.org/abs/1511.04108.pdf.
[15] ZHANG S, ZHANG X, WANG H, et al. Chinese medical question answer matching using end-to-end character-level multi-scale CNNs[J]. Applied Sciences, 2017, 7(8):767.
[16] BENGIO Y, DUCHARME R, VINCENT P, et al. A neural probabilistic language model[J]. Journal of Machine Learning Research, 2003, 3(6):1137-1155.
[17] MIKOLOV T, SUTSKEVER I, CHEN K, et al. Distributed representations of words and phrases and their compositionality[EB/OL].[2018-08-23]. http://papers.nips.cc/paper/5021-distributed-representations-of-words-and-phrases-and-their-compositionality.pdf.
[18] WANG Z G, HAMZA W, FLORIAN R. Bilateral multi-perspective matching for natural language sentences[EB/OL].[2018-08-20]. https://arxiv.org/abs/1702.03814.pdf.
[19] TADDY M. Document classification by inversion of distributed language representations[EB/OL].[2018-08-20]. https://arxiv.org/abs/1504.07295.pdf.
[20] LIN Y K, LIU Z Y, SUN M S, et al. Learning entity and relation embeddings for knowledge graph completion[C]//AAAI 2014:Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence. Menlo Park, CA:AAAI, 2015:2181-2187.
[21] ZHANG M S, ZHANG Y, CHE W X, et al. Character-level Chinese dependency parsing[C]//Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics. Cambridge, MA:MIT Press, 2014:1326-1336.
[22] CHUNG J, CHO K, BENGIO Y. A character-level decoder without explicit segmentation for neural machine translation[EB/OL].[2018-08-15]. https://arxiv.org/abs/1603.06147.pdf.
[23] ZHANG X, ZHAO J B, LECUN Y. Character-level convolutional networks for text classification[C]//NIPS 2015:Proceedings of the 28th International Conference on Neural Information Processing Systems. Cambridge, MA:MIT Press, 2015:649-657.
[24] GOLUB D, HE X D. Character-level question answering with attention[C]//Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing. Cambridge, MA:MIT Press, 2016:1598-1607.

基于注意力和字嵌入的中文医疗问答匹配方法

Chinese medical question answer matching method based on attention mechanism and character embedding

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]	宋中山, 梁家锐, 郑禄, 刘振宇, 帖军. 基于双向门控尺度特征融合的遥感场景分类[J]. 计算机应用, 2021, 41(9): 2726-2735.
[2]	李康康, 张静. 基于注意力机制的多层次编码和解码的图像描述模型[J]. 计算机应用, 2021, 41(9): 2504-2509.
[3]	张永斌, 常文欣, 孙连山, 张航. 基于字典的域名生成算法生成域名的检测方法[J]. 计算机应用, 2021, 41(9): 2609-2614.
[4]	赵宏, 孔东一. 图像特征注意力与自适应注意力融合的图像内容中文描述[J]. 计算机应用, 2021, 41(9): 2496-2503.
[5]	徐江浪, 李林燕, 万新军, 胡伏原. 结合目标检测的室内场景识别方法[J]. 计算机应用, 2021, 41(9): 2720-2725.
[6]	牟长宁, 王海鹏, 周丕宇, 侯鑫行. 基于图卷积神经网络的串联质谱从头测序[J]. 计算机应用, 2021, 41(9): 2773-2779.
[7]	王贺兵, 张春梅. 基于非对称卷积-压缩激发-次代残差网络的人脸关键点检测[J]. 计算机应用, 2021, 41(9): 2741-2747.
[8]	谢德峰, 吉建民. 融入句法感知表示进行句法增强的语义解析[J]. 计算机应用, 2021, 41(9): 2489-2495.
[9]	代雨柔, 杨庆, 张凤荔, 周帆. 基于自监督学习的社交网络用户轨迹预测模型[J]. 计算机应用, 2021, 41(9): 2545-2551.
[10]	刘雅璇, 钟勇. 基于头实体注意力的实体关系联合抽取方法[J]. 计算机应用, 2021, 41(9): 2517-2522.
[11]	周险兵, 樊小超, 任鸽, 杨勇. 基于多层次语义特征的英文作文自动评分方法[J]. 计算机应用, 2021, 41(8): 2205-2211.
[12]	曹玉红, 徐海, 刘荪傲, 王紫霄, 李宏亮. 基于深度学习的医学影像分割研究综述[J]. 计算机应用, 2021, 41(8): 2273-2287.
[13]	秦斌斌, 彭良康, 卢向明, 钱江波. 司机分心驾驶检测研究进展[J]. 计算机应用, 2021, 41(8): 2330-2337.
[14]	黄程程, 董霄霄, 李钊. 基于二维Winograd算法的深流水线5×5卷积方法[J]. 计算机应用, 2021, 41(8): 2258-2264.
[15]	曾祥银, 郑伯川, 刘丹. 基于深度卷积神经网络和聚类的左右轨道线检测[J]. 计算机应用, 2021, 41(8): 2324-2329.