基于双向LSTM的军事命名实体识别
|
摘要
为了减少传统的命名实体识别需要人工制定特征的大量工作,通过无监督训练获得军事领域语料的分布式向量表示,采用双向LSTM递归神经网络模型解决军事领域命名实体的识别问题,并且通过添加字词结合的输入向量和注意力机制对双向LSTM递归神经网络模型进行扩展和改进,进而提高军事领域命名实体识别。实验结果表明,提出的方法能够完成军事领域命名实体的识别,并且在测试集语料上的F-值达到了87.38%。
In order to reduce the large amount of work that traditional named entity recognition needs to manually formulate features,we obtain distributed vector representations of the military domain corpus through unsupervised training,and utilize the bidirectional LSTM(BLSTM)recursive neural network model to solve the identification problem of named entities in the military field.The BLSTM recursive neural network model is extended and improved by adding word-binding input vectors and attention mechanism to enhance the recognition of named entities in the military field.Experimental results show that the proposed method can identify named entities in the military field,and the F-value in the test set corpus reaches 87.38%.
In order to reduce the large amount of work that traditional named entity recognition needs to manually formulate features,we obtain distributed vector representations of the military domain corpus through unsupervised training,and utilize the bidirectional LSTM(BLSTM)recursive neural network model to solve the identification problem of named entities in the military field.The BLSTM recursive neural network model is extended and improved by adding word-binding input vectors and attention mechanism to enhance the recognition of named entities in the military field.Experimental results show that the proposed method can identify named entities in the military field,and the F-value in the test set corpus reaches 87.38%.
引文
[1]Zhou G D,Su J.Machine learning-based named entity recognition via effective integration of various evidences[J].Natural Language Engineering,2005,11(2):189-206.
[2]Li L S,Zhou R P,Huang D G.Two-phase biomedical named entity recognition using CRFs[J].Computational Biology&Chemistry,2009,33(4):334-338.
[3]Wu Y H,Jiang M,Lei J B,et al.Named entity recognition in Chinese clinical text using deep network[J].Studies in Health Technology and Information,2015,216:624-628.
[4]Huang Z,Xu W,Yu K.Bidirectional LSTM-CRF models for sequence tagging[J].Computer Science,arXiv:1508.0199|v|:2015.
[5]Mccallum A,Li Wei.Early results for named entity recognition with conditional random fields,feature induction and web-enhanced lexicons[C]∥Proc of NAACL-HLT 2003,2003:188-191.
[6]Isozaki H,Kazawa H.Efficient support vector classifiers for named entity recognition[C]∥Proc of the 19th International Conference on Computational Linguistics,2002:390-396.
[7]Chiu J P C,Nichols E.Named entity recognition with bidirectional LSTM-CNNs[J].Computer Science,arXiv:1511.08308:2015.
[8]Soutner D,Müller L.Continuous distributed representations of words as input of LSTM network language model[C]∥Proc of International Conference on Text,Speech,and Dialogue,2014:150-157.
[9]Hao Z F,Wang H F,Cai R C,et al.Product named entity recognition for Chinese query questions based on a skip-chain CRF model[J].Neural Computing&Applications,2013,23(2):371-379.
[10]Patra R,Saha S K.A kernel-based approach for biomedical named entity recognition[J].The Scientific World Journal,2013(2):950796.
[11]Zheng X Q,Chen H Y,Xu T Y.Deep learning for Chinese word segmentation and POS tagging[C]∥Proc of the 2013Conference on Empirical Methods in Natural Language Processing,2013:647-657.
[12]Mikolov T,Yih W T,Zweig G.Linguistic regularities in continuous space word representations[C]∥Proc of NAACL-HLT 2013,2013:746-751.
[2]Li L S,Zhou R P,Huang D G.Two-phase biomedical named entity recognition using CRFs[J].Computational Biology&Chemistry,2009,33(4):334-338.
[3]Wu Y H,Jiang M,Lei J B,et al.Named entity recognition in Chinese clinical text using deep network[J].Studies in Health Technology and Information,2015,216:624-628.
[4]Huang Z,Xu W,Yu K.Bidirectional LSTM-CRF models for sequence tagging[J].Computer Science,arXiv:1508.0199|v|:2015.
[5]Mccallum A,Li Wei.Early results for named entity recognition with conditional random fields,feature induction and web-enhanced lexicons[C]∥Proc of NAACL-HLT 2003,2003:188-191.
[6]Isozaki H,Kazawa H.Efficient support vector classifiers for named entity recognition[C]∥Proc of the 19th International Conference on Computational Linguistics,2002:390-396.
[7]Chiu J P C,Nichols E.Named entity recognition with bidirectional LSTM-CNNs[J].Computer Science,arXiv:1511.08308:2015.
[8]Soutner D,Müller L.Continuous distributed representations of words as input of LSTM network language model[C]∥Proc of International Conference on Text,Speech,and Dialogue,2014:150-157.
[9]Hao Z F,Wang H F,Cai R C,et al.Product named entity recognition for Chinese query questions based on a skip-chain CRF model[J].Neural Computing&Applications,2013,23(2):371-379.
[10]Patra R,Saha S K.A kernel-based approach for biomedical named entity recognition[J].The Scientific World Journal,2013(2):950796.
[11]Zheng X Q,Chen H Y,Xu T Y.Deep learning for Chinese word segmentation and POS tagging[C]∥Proc of the 2013Conference on Empirical Methods in Natural Language Processing,2013:647-657.
[12]Mikolov T,Yih W T,Zweig G.Linguistic regularities in continuous space word representations[C]∥Proc of NAACL-HLT 2013,2013:746-751.