医疗问题诉求分类属于文本分类,是自然语言处理中的基础任务。该文提出一种基于强化学习的方法对医疗问题诉求进行分类。首先,通过强化学习自动识别出医疗问题中的关键词,并且对医疗问题中的关键词和非关键词赋予不同的值构成一个向量;其次,利用该向量作为attention机制的权重向量,对Bi-LSTM模型生成的隐含层状态序列加权求和得到问题表示;最后通过Softmax分类器对问题表示进行分类。实验结果表明,该方法比基于Bi-LSTM模型的分类结果准确率提高1.49%。
Abstract
Medical question appeal classification can be dealt with as a text classification issue. This paper presents a reinforcement learning method for medical question appeal classification. Firstly, the keywords in medical problems are automatically identified by reinforcement learning, and the keywords and non-keywords in medical problems are assigned different values to constitute a vector. Secondly, the vector is set as the weight vector of the attention mechanism, and the weighted sum of the hidden layer generated by the Bi-LSTM model constitute question representation. At last, the question representation is classified by softmax classifier. Experimental results show that the accuracy of this method outperforms Bi-LSTM model by 1.49%.
关键词
强化学习 /
Bi-LSTM /
注意力机制
{{custom_keyword}} /
Key words
reinforcement learning /
Bi-LSTM /
attention mechanism
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] Socher R, Perelygin A, Wu Je, et al. Recursive deep models for semantic compositionality over a sentiment treebank[C]//Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing (EMNLP13), 2013: 1631-1642.
[2] Socher R, Huval B, Manning CD, et al. Semantic compositionality through recursive matrix-vector spaces[C]//Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, 2012: 1201-1211.
[3] Cho K, Merrinboer BV, Gulcehre C, et al. Learning phrase representations using RNN encoder-decoder for statistical machine translation[C]//Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2012: 1724-1734,
[4] Hill F, Cho K, Korhonen A. Learning distributed re-presentations of sentences from unlabelled data[C]//Proceedings of Annual Conference of the North American Chapter of the Association for Computational Linguistics, 2016: 1367-1377.
[5] Yin W, Kann K, Yu M, et al. Comparative study of CNN and RNN for natural language processing[J]. arXiv preprint arXiv: 1702.01923, 2017.
[6] Wen Y, Zhang W, Luo R, et al. Learning text representation using recurrent convolutional neural network with high way layers[J]. arXiv preprintar Xiv: 1606.06905, 2016.
[7] He H, Gimpel K, Lin J. Multi-perspective sentence similarity modeling with convolutional neural networks[C]//Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, 2015: 1576-1586.
[8] Lai SW, Xu LH, Liu K, et al. Recurrent convolutional neural networks for text classification[C]//Proceedings of the 29th AAAI Conference on Artificial Intelligence (AAAI'15), 2015: 2267-2273.
[9] Hochreiter S, Schmidhuber J. Long short-term memory[J]. Neural Computation, 1997: 1735-1780.
[10] Zhang Y, Liu Q, Song L. Sentence-state LSTM for text representation[C]//Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Long Papers), 2018: 317-327.
[11] Tai KS, Socher R, Manning CD. Improved semantic representations from tree-structured long short-term memory networks[C]//Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics, 2015: 1556-1566
[12] Zhang T, Huang M, Zhao L. Learning structured representation for text classification via reinforcement learning[C]//Proceedings of the 32nd AAAI Conference on Artificial Intelligence, 2018: 6053-6060.
[13] Yogatama D, Blunsom P, Dyer C, et al. Learning to compose words into sentences with reinforcement learning[C]//Proceedings of International Conference on Learning Representations,2017:1-10.
[14] Williams R J. Simple statistical gradient-following algorithms for connectionist reinforcement learning[J]. Machine Learning, 1992, 8(3-4): 229-256.
[15] Sutton R S, McAllester D, Singh S, et al. Policy gradient methods for reinforcement learning with function approximation[C]//Proceedings of the 12th International Conference on Neural Information Processing Systems,1999: 1057-1063.
[16] Graves A, Mohamed A R, Hinton G. Speech recognition with deep recurrent neural networks[C]//Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing, 2013: 6645-6649.
[17] Lin Z, Feng M, Santos CN, et al. A structured self-attentive sentence embedding[C]//Proceedings of the International Conference on Learning Representations, 2017.
[18] Mikolov T, Sutskever I, Chen K, et al. Distributed representations of words and phrases and their compositionality[C]//Proceedings of the 26th International Conference on Neural Information Processing Systems, 2013, 26: 3111-3119.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
基金
国家自然科学基金(U1936109,61672127)
{{custom_fund}}
PDF(1370 KB)
