406
J. Ren et al.
4 Conclusion
In order to solve the problem that traditional BiLSTM can not obtain deeper
latent semantics, we change the BiLSTM model, and successfully combine it with
a probabilistic graphic model (CRF layer) to gain a better prediction accuracy
in NER problem. After experiments, we can find that it is useful in Chinese NER
question, and it has the highest CRF viterbi accuracy.
Acknowledgements. This work was supported by the National Natural Science
Foundation of China (61731006, 61671138), and was partly supported by the 111
Project No. B17008.
References
1. Zhao S (2004) Named entity recognition in biomedical texts using an HMM model.
In: International joint workshop on natural language processing in biomedicine and
its applications. Association for Computational Linguistics
2. Ponomareva N , Pla F , Molina A et al (2007) Biomedical named entity recognition:
a poor knowledge HMM-based approach
3. Koller D, Friedman N (2009) Probabilistic graphical models: principles and techniques. MIT Press
4. Lafferty J, McCallum A, Pereira F (2001) Conditional random fields: probabilistic
models for segmenting and labeling sequence data. In: International conference of
machine learning
5. Zhang Y , Yang J (2018) Chinese NER using lattice LSTM
6. Huang Z, Xu W, Yu K (2015) Bidirectional LSTM-CRF models for sequence tagging. Comput Sci
7. Xu C, Xie L, Xiao X (2018 July) A bidirectional LSTM and conditional random
fields approach to medical named entity recognition 90(7):1063–1075
8. Ma X, Hovy E (2016) End-to-end sequence labeling via bi-directional LSTMCNNs-CRF
9. Lample G, Ballesteros M Subramanian S et al (2016) Neural architectures for
named entity recognition
10. Zheng S, Wang F, Bao H et al (2017) Joint extraction of entities and relations
based on a novel tagging scheme
J. Ren et al.
4 Conclusion
In order to solve the problem that traditional BiLSTM can not obtain deeper
latent semantics, we change the BiLSTM model, and successfully combine it with
a probabilistic graphic model (CRF layer) to gain a better prediction accuracy
in NER problem. After experiments, we can find that it is useful in Chinese NER
question, and it has the highest CRF viterbi accuracy.
Acknowledgements. This work was supported by the National Natural Science
Foundation of China (61731006, 61671138), and was partly supported by the 111
Project No. B17008.
References
1. Zhao S (2004) Named entity recognition in biomedical texts using an HMM model.
In: International joint workshop on natural language processing in biomedicine and
its applications. Association for Computational Linguistics
2. Ponomareva N , Pla F , Molina A et al (2007) Biomedical named entity recognition:
a poor knowledge HMM-based approach
3. Koller D, Friedman N (2009) Probabilistic graphical models: principles and techniques. MIT Press
4. Lafferty J, McCallum A, Pereira F (2001) Conditional random fields: probabilistic
models for segmenting and labeling sequence data. In: International conference of
machine learning
5. Zhang Y , Yang J (2018) Chinese NER using lattice LSTM
6. Huang Z, Xu W, Yu K (2015) Bidirectional LSTM-CRF models for sequence tagging. Comput Sci
7. Xu C, Xie L, Xiao X (2018 July) A bidirectional LSTM and conditional random
fields approach to medical named entity recognition 90(7):1063–1075
8. Ma X, Hovy E (2016) End-to-end sequence labeling via bi-directional LSTMCNNs-CRF
9. Lample G, Ballesteros M Subramanian S et al (2016) Neural architectures for
named entity recognition
10. Zheng S, Wang F, Bao H et al (2017) Joint extraction of entities and relations
based on a novel tagging scheme