無中文摘要

Many websites offer QA (question & answering) services related to medical and health information. e.g. The Chinese medical QA system: 120ask. While the website provides a platform of interactions between patients and doctors, the QA reviewing process still requires time from both the parties and doctors. A possible improvement to speed up the responses of doctors is to provide an automatically diagnose of the users’ diseases based on their descriptions. In this thesis, we propose a system which can extract the colloquial symptoms from the text descriptions of users automatically. The system aims to extract the medical terms by processing medical intent sentence classification and word types labeling. The medical intent sentence classification is to classify whether a sentence contains symptom relative descriptions. The word type labeling is to label the type of words which are related to medical information. We implemented these two tasks by a biLSTM neural network. Besides, the multi-task learning strategy is used to share the implicit features information and optimize the loss functions of both ones. In addition, we added the global features, which are learned from medical sentence intent classification, to enhance the performance of word types labeling.

[1] A. Akbik, D. Blythe and R. Vollgraf, "Contextual string embeddings for sequence labeling," Proceedings of the 27th International Conference on Computational Linguistics, pp. 1638--1649, 2018.
[2] A. Kendall, Y. Gal and R. Cipolla, "Multi-task learning using uncertainty to weigh losses for scene geometry and semantics," Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7482--7491, 2018.
[3] B. Fortuner, "ML Cheatsheet-Loss Functions," [Online]. Available: https://ml-cheatsheet.readthedocs.io/en/latest/loss_functions.html.
[4] B. He, Y. Guan and R. Dai, "Classifying medical relations in clinical text via convolutional neural networks," Artificial intelligence in medicine, vol. 93, pp. 43--49, 2019.
[5] B. Ji, R. Liu, S. Li, J. Yu, Q. Wu, Y. Tan and J. Wu, "A hybrid approach for named entity recognition in Chinese electronic medical record," BMC medical informatics and decision making, vol. 19, no. 2, p. 64, 2019.
[6] B. Tang, X. Wang, J. Yan and Q. Chen, "Entity recognition in Chinese clinical text using attention-based CNN-LSTM-CRF," BMC medical informatics and decision making, vol. 19, no. 3, p. 74, 2019.
[7] D. Raj, S. Sahu and A. Anand, "Learning local and global contexts using a convolutional recurrent network model for relation classification in biomedical text," Proceedings of the 21st conference on computational natural language learning (CoNLL 2017), pp. 311--321, 2017.
[8] F. Wang, Z. Wang, Z. Li and J.-R. Wen, "Concept-based short text classification and ranking," Proceedings of the 23rd ACM International Conference on Conference on Information and Knowledge Management, pp. 1069--1078, 2014.
[9] J. Chen, Y. Hu, J. Liu, Y. Xiao and H. Jiang, "Deep short text classification with knowledge powered attention," arXiv preprint arXiv:1902.08050, 2019.
[10] J. Lafferty, A. McCallum and F. C. Pereira, "Conditional random fields: Probabilistic models for segmenting and labeling sequence data," 2001.
[11] J. Sun., "Jieba, chinese word segmentation tool," 2012. [Online]. Available: https://github.com/fxsjy/jieba.
[12] J. Zhou, J. Chen and J. Ye, "Multi-task learning: Theory, algorithms, and applications," in SDM tutorials, 2012.
[13] K. Lounici, M. Pontil, A. B. Tsybakov and S. Van De Geer, "Taking advantage of sparsity in multi-task learning," in arXiv preprint arXiv:0903.1468, 2009.
[14] K. Yano, "Neural Disease Named Entity Extraction with Character-based BiLSTM+ CRF in Japanese Medical Text," arXiv preprint arXiv:1806.03648, 2018.
[15] M. Ju, M. Miwa and S. Ananiadou, "A neural layered model for nested named entity recognition," Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), pp. 1446--1459, 2018.
[16] O. Bodenreider, "The unified medical language system (UMLS): integrating biomedical terminology," Nucleic acids research, vol. 32, no. suppl_1, pp. D267--D270, 2004.
[17] P. Liu, "Introduction of Conditional Random Fields," [Online]. Available: https://www.cnblogs.com/pinard/p/7048333.html.
[18] R. Caruana, "Multitask learning," Machine learning, vol. 28, no. 1, pp. 41--75, 1997.
[19] R. Collobert and J. Weston, "A unified architecture for natural language processing: Deep neural networks with multitask learning," in Proceedings of the 25th international conference on Machine learning, ACM, 2008, pp. 160--167.
[20] R. Feldman, O. Netzer, A. Peretz and B. Rosenfeld, "Utilizing text mining on online medical forums to predict label change due to adverse drug reactions," Proceedings of the 21th ACM SIGKDD international conference on knowledge discovery and data mining, pp. 1779--1788, 2015.
[21] R. R. a. P. Sojka, "Word2vec embeddings," 2010. [Online]. Available: https://radimrehurek.com/gensim/models/word2vec.html.
[22] S. K. Sahu, A. Anand, K. Oruganty and M. Gattu, "Relation extraction from clinical texts using domain invariant convolutional neural network," arXiv preprint arXiv:1606.09370, 2016.
[23] S. Ruder, "An overview of multi-task learning in deep neural networks," arXiv preprint arXiv:1706.05098, 2017.
[24] T. Goodwin and S. Harabagiu, "Medical question answering for clinical decision support," 25th ACM international on conference on information and knowledge management, p. 297~306, 2016.
[25] W. contributors, "Multi-task learning," Wikipedia, The Free Encyclopedia, 2019. [Online]. Available:
https://en.wikipedia.org/w/index.php?title=Multi-task_learning&oldid=890283180.
[26] W. contributors, "Softmax function," Wikipedia, The Free Encyclopedia, 2019. [Online]. Available: https://en.wikipedia.org/w/index.php?title=Softmax_function&oldid=903563960.
[27] W. contributors, "Unified Medical Language System," Wikipedia, The Free Encyclopedia, 2019. [Online]. Available: https://en.wikipedia.org/w/index.php?title=Unified_Medical_Language_System&oldid=899674969.
[28] W. contributors, "Word embedding Wikipedia, The Free Encyclopedia," 2019. [Online]. Available: https://en.wikipedia.org/w/index.php?title=Word_embedding&oldid=88292196.
[29] W. contributors, "Word embedding," Wikipedia, The Free Encyclopedia, 2019. [Online]. Available: https://en.wikipedia.org/w/index.php?title=Word_embedding&oldid=88292196.
[30] Y. Jo, N. Loghmanpour and C. P. Rosé, "Time series analysis of nursing notes for mortality prediction via a state transition topic model," Proceedings of the 24th ACM international on conference on information and knowledge management, pp. 1171--1180, 2015.
[31] Yao, Yushi and Z. Huang, "Bi-directional LSTM recurrent neural network for Chinese word segmentation," International Conference on Neural Information Processing, pp. 345--353, 2016.
[32] Y. Zhang and D.-Y. Yeung, "A convex formulation for learning task relationships in multi-task learning," in arXiv preprint arXiv:1203.3536, 2012.
[33] Zhuhai Health Cloud Technology Co., Ltd., "120ask.com," 2002. [Online]. Available: https://www.120ask.com.