Chinese Medical Question Answer Matching Using End-to-End Character-Level Multi-Scale CNNs
Source abstract
Abstract
This paper focuses mainly on the problem of Chinese medical question answer matching, which is arguably more challenging than open-domain question answer matching in English due to the combination of its domain-restricted nature and the language-specific features of Chinese. We present an end-to-end character-level multi-scale convolutional neural framework in which character embeddings instead of word embeddings are used to avoid Chinese word segmentation in text preprocessing, and multi-scale convolutional neural networks (CNNs) are then introduced to extract contextual information from either question or answer sentences over different scales. The proposed framework can be trained with minimal human supervision and does not require any handcrafted features, rule-based patterns, or external resources. To validate our framework, we create a new text corpus, named cMedQA, by harvesting questions and answers from an online Chinese health and wellness community. The experimental results on the cMedQA dataset show that our framework significantly outperforms several strong baselines, and achieves an improvement of top-1 accuracy by up to 19%.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Topic Modeling · Natural Language Processing Techniques · Advanced Text Analysis Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
College of Information Systems and Management, National University of Defense Technology, Changsha 410073, China
Funding
National Natural Science Foundation of China
References (43)
Show source-provided references
1. Feng, M., Xiang, B., Glass, M.R., Wang, L., and Zhou, B. (2015, January 13–17). Applying deep learning to answer selection: A study and an open task. Proceedings of the 2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), Scottsdale, AZ, USA.10.1109/ASRU.2015.7404872 ↗
2. Tan, M., dos Santos, C., Xiang, B., and Zhou, B. (2016, January 7–12). Improved representation learning for question answer matching. Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, Berlin, Germany.10.18653/v1/P16-1044 ↗
3. Qiu, X., and Huang, X. (2015, January 25–31). Convolutional Neural Tensor Network Architecture for Community-Based Question Answering. Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence (IJCAI), Buenos Aires, Argentina.
4. Jain, S., and Dodiya, T. (2012, January 28–30). Rule Based Architecture for Medical Question Answering System. Proceedings of the Second International Conference on Soft Computing for Problem Solving (SocProS 2012), Rajasthan, India.
5. Wang, J., Man, C., Zhao, Y., and Wang, F. (2016, January 10–12). An answer recommendation algorithm for medical community question answering systems. Proceedings of the 2016 IEEE International Conference on Service Operations and Logistics, and Informatics (SOLI), Beijing, China.10.1109/SOLI.2016.7551676 ↗
6. Ben Abacha, A., and Zweigenbaum, P. (2012, January 28–30). Medical question answering: Translating medical questions into sparql queries. Proceedings of the 2nd ACM SIGHIT International Health Informatics Symposium, Miami, FL, USA.10.1145/2110363.2110372 ↗
7. MEANS: A medical question-answering system combining NLP techniques and semantic Web technologies10.1016/j.ipm.2015.04.006 ↗
8. Li, C. (2016). Research and Application on Intelligent Disease Guidance and Medical Question Answering Method. [Master’s Thesis, Dalian University of Technology].
9. The probabilistic relevance framework: BM25 and beyond10.1561/1500000019 ↗
10. Mihalcea, R., and Tarau, P. (2004). TextRank: Bringing Order into Texts, Association for Computational Linguistics.
11. Goodwin, T.R., and Harabagiu, S.M. (2016, January 24–28). Medical Question Answering for Clinical Decision Support. Proceedings of the 25th ACM International on Conference on Information and Knowledge Management, Indianapolis, IN, USA.10.1145/2983323.2983819 ↗
12. State-of-the-art in biomedical literature retrieval for clinical cases: A survey of the TREC 2014 CDS track10.1007/s10791-015-9259-x ↗
13. Li, X., and Croft, W.B. (2001, January 18–21). Evaluating question-answering techniques in Chinese. Proceedings of the First International Conference on Human language Technology Research, San Diego, CA, USA.10.3115/1072133.1072173 ↗
14. Semantic computation in a Chinese question-answering system10.1007/BF02960786 ↗
15. Li, T., Hao, Y., Zhu, X., and Zhang, X. (2014). A Chinese question answering system for specific domain. WAIM 2014: Web-Age Information Management, Proceedings of the International Conference on Web-Age Information Management, Macau, China, 3–5 June 2014, Springer.10.1007/978-3-319-08010-9_64 ↗
16. Wang, B., Niu, J., Ma, L., Zhang, Y., Zhang, L., Li, J., Zhang, P., and Song, D. (2016). A Chinese Question Answering Approach Integrating Count-Based and Embedding-Based Features. Natural Language Understanding and Intelligent Applications, Proceedings of the International Conference on Computer Processing of Oriental Languages, Kunming, China, 2–6 December 2016, Springer.10.1007/978-3-319-50496-4_88 ↗
17. Hu, B., Lu, Z., Li, H., and Chen, Q. (2014, January 8–13). Convolutional neural network architectures for matching natural language sentences. Proceedings of the Advances in Neural Information Processing Systems, Montreal, QC, Canada.
18. Zhou, X., Hu, B., Chen, Q., Tang, B., and Wang, X. (arXiv, 2015). Answer sequence learning with neural networks for answer selection in community question answering, arXiv.10.3115/v1/P15-2117 ↗
19. Tan, M., Xiang, B., and Zhou, B. (arXiv, 2015). LSTM-based Deep Learning Models for non-factoid answer selection, arXiv.
20. A neural probabilistic language model
21. Mikolov, T., Sutskever, I., Chen, K., Corrado, G., and Dean, J. (arXiv, 2013). Distributed Representations of Words and Phrases and their Compositionality, arXiv.
22. Taddy, M. (arXiv, 2015). Document Classification by Inversion of Distributed Language Representations, arXiv.10.3115/v1/P15-2008 ↗
23. Huang, C., Qiu, X., and Huang, X. (2014). Text classification with document embeddings. Chinese Computational Linguistics and Natural Language Processing Based on Naturally Annotated Big Data, Springer.10.1007/978-3-319-12277-9_12 ↗
24. Wang, Z., Zhang, J., Feng, J., and Chen, Z. (2014, January 27–31). Knowledge Graph Embedding by Translating on Hyperplanes. Proceedings of the Twenty-Eighth AAAI Conference on Artificial Intelligence, Québec City, QC, Canada.10.1609/aaai.v28i1.8870 ↗
25. Lin, Y., Liu, Z., Sun, M., Liu, Y., and Zhu, X. (2015, January 25–30). Learning Entity and Relation Embeddings for Knowledge Graph Completion. Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence (AAAI), Austin, TX, USA.10.1609/aaai.v29i1.9491 ↗
26. Levy, O., and Goldberg, Y. (2014, January 8–13). Neural word embedding as implicit matrix factorization. Proceedings of the Advances in Neural Information Processing Systems, Montreal, QC, Canada.
27. Yang, C., and Liu, Z. (arXiv, 2015). Comprehend deepwalk as matrix factorization, arXiv.
28. Zhang, M., Zhang, Y., Che, W., and Liu, T. (2014, January 23–25). Character-level chinese dependency parsing. Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics, Baltimore, MD, USA.10.3115/v1/P14-1125 ↗
29. Ling, W., Trancoso, I., Dyer, C., and Black, A.W. (arXiv, 2015). Character-based neural machine translation, arXiv.
30. Chung, J., Cho, K., and Bengio, Y. (arXiv, 2016). A character-level decoder without explicit segmentation for neural machine translation, arXiv.10.18653/v1/P16-1160 ↗
31. Luong, M.T., and Manning, C.D. (arXiv, 2016). Achieving open vocabulary neural machine translation with hybrid word-character models, arXiv.10.18653/v1/P16-1100 ↗
32. Costa-Jussa, M.R., and Fonollosa, J.A. (arXiv, 2016). Character-based neural machine translation, arXiv.10.18653/v1/W17-4123 ↗
33. Zhang, X., Zhao, J., and LeCun, Y. (2015, January 7–12). Character-level convolutional networks for text classification. Proceedings of the Advances in Neural Information Processing Systems, Montreal, QC, Canada.
34. Golub, D., and He, X. (arXiv, 2016). Character-level question answering with attention, arXiv.
35. Kalchbrenner, N., Grefenstette, E., Blunsom, P., Kartsaklis, D., and Sadrzadeh, M. (2014, January 22–27). A Convolutional Neural Network for Modelling Sentences. Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics, Baltimore, MD, USA.10.3115/v1/P14-1062 ↗
36. Kim, Y. (2014, January 25–29). Convolutional Neural Networks for Sentence Classification. Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), Doha, Qatar.10.3115/v1/D14-1181 ↗
37. ABCNN: Attention-Based Convolutional Neural Network for Modeling Sentence Pairs10.1162/tacl_a_00097 ↗
38. Medical information retrieval: Introduction to the special issue10.1007/s10791-015-9277-8 ↗
39. Introduction to information retrieval
40. Hsu, W.N., Zhang, Y., and Glass, J. (arXiv, 2016). Recurrent Neural Network Encoder with Attention for Community Question Answering, arXiv.
41. Chung, J., Ahn, S., and Bengio, Y. (arXiv, 2016). Hierarchical multiscale recurrent neural networks, arXiv.
42. Cui, Y., Liu, T., Chen, Z., Wang, S., and Hu, G. (arXiv, 2016). Consensus attention-based neural networks for chinese reading comprehension, arXiv.10.18653/v1/P17-1055 ↗
43. Yu, L., Hermann, K.M., Blunsom, P., and Pulman, S. (arXiv, 2014). Deep learning for answer sentence selection, arXiv.