最近,将词嵌入融合到基于字嵌入的模型已经被证明是有效的。但是,大多数现有的研究都忽视了对部首信息的使用。该文提出一种将词嵌入、字嵌入和部首嵌入相融合的新方法,该方法利用词嵌入和字嵌入的优点,并考虑了部首中包含的大量语义信息,从而充分利用了不同粒度的语义信息,提高了模型的识别效果。该方法在Weibo数据集和MSRA数据集上的实验结果表明,该文所提方法较相关方法在识别精度上取得提升。
Abstract
Recently, integrating word information into character-based model has been proved to be effective for Chinese named entity recognition. To capture Chinese radicals with a large amount of semantic information, we propose a new model integrating word embedding and radical embedding into character-based model, so as to leverage semantics of different granularities information and improve the recognition accuracy. The experimental results on the Weibo dataset and MSRA dataset show that the proposed model has improved recognition accuracy compared with related models.
关键词
命名实体识别 /
多重嵌入 /
注意力机制 /
部首信息
{{custom_keyword}} /
Key words
named entity recognition /
multiple embeddings /
attention mechanism /
radical information
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] NADEAU D, SEKINE S. A survey of named entity recognition and classification[J]. Lingvisticae Investigationes, 2007, 30(1): 3-26.
[2] VIRGA P, KHUDANPUR S. Transliteration of proper names in cross-lingual information retrieval[C]//Proceedings of the ACL Workshop on Multilingual and Mixed-language Named Entity Recognition, 2003: 57-64.
[3] MIWA M, BANSAL M. End-to-end relation extraction using LSTMs on sequences and tree structures[C]//Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, 2016: 1105-1116.
[4] MOLLA D, VAN ZAANEN M, SMITH D. Named entity recognition for question answering[C]//Proceedings of the Australasian Language Technology Workshop, 2006: 51-58.
[5] ZHONG Q, TANG Y. An Attention-Based BiLSTM-CRF for Chinese named entity recognition[C]//Proceedings of the IEEE 5th International Conference on Cloud Computing and Big Data Analytics. IEEE, 2020: 550-555.
[6] HE, H F, SUN X. F-score driven max margin neural network for named entity recognition in Chinese social media[C]//Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics, 2017: 713-718.
[7] HE H, SUN X. A unified model for cross-domain and semi-supervised named entity recognition in Chinese social media[C]//Proceedings of the AAAI Conference on Artificial Intelligence, 2017: 3216-3222.
[8] HE J, WANG H. Chinese named entity recognition and word segmentation based on character[C]//Proceedings of the 6th SIGHAN Workshop on Chinese Language Processing, 2008.
[9] LI H, HAGIWARA M, LI Q, et al. Comparison of the impact of word segmentation on name tagging for Chinese and Japanese[C]//Proceedings of the 9th International Conference on Language Resources and Evaluation, 2014: 2532-2536.
[10] LIU Z, ZHU C, ZHAO T. Chinese named entity recognition with a sequence labeling approach: based on characters, or based on words?[C]//Proceedings of the Advanced Intelligent Computing Theories and Applications. Springer, Berlin, Heidelberg, 2010: 634-640.
[11] ZHANG Y, YANG J. Chinese NER using lattice LSTM[C]//Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, 2018: 1554-1564.
[12] LAFFERTY J D, MCCALLUM A, PEREIRA F C N. Conditional random fields: Probabilistic models for segmenting and labeling sequence Data[C]//Proceedings of the 18th International Conference on Machine Learning, 2001: 282-289.
[13] HAMMERTON J. Named entity recognition with long short-term memory[C]//Proceedings of the 7th Conference on Natural Language Learning at HLT-NAACL, 2003: 172-175.
[14] COLLOBERT R, WESTON J, BOTTOU L, et al. Natural language processing (almost) from scratch[J]. Journal of Machine Learning Research, 2011, 12: 2493-2537.
[15] HUANG Z, XU W, YU K. Bidirectional LSTM-CRF models for sequence tagging[J]. arXiv preprint arXiv:1508.01991, 2015.
[16] LAMPLE G, BALLESTEROS M, SUBRAMANIAN S, et al. Neural architectures for named entity recognition[C]//Proceedings of NAACL, 2016: 260-270.
[17] XIANG Y. Chinese named entity recognition with character-word mixed embedding[C]//Proceedings of the ACM on Conference on Information and Knowledge Management, 2017: 2055-2058.
[18] GUI T, MA R, ZHANG Q, et al. CNN-based Chinese NER with lexicon rethinking[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, 2019: 1039-1049.
[19] DONG C, ZHANG J, ZONG C, et al. Character-based LSTM-CRF with radical-level features for Chinese named entity recognition[M]. Natural Language Understanding and Intelligent Applications. Springer, Cham, 2016: 239-250.
[20] ZHU Y, WANG G. CAN-NER: Convolutional attention network for Chinese named entity recognition[C]//Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2019: 3384-3393.
[21] VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems, 2017: 5998-6008.
[22] HOCHREITER S, SCHMIDHUBER J. Long short-term memory[J]. Neural Computation, 1997, 9(8): 1735-1780.
[23] LUONG M T, PHAM H, MANNING C D. Effective approaches to attention-based neural machine translation[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing, 2015: 1412-1421.
[24] LIU G, GUO J. Natural language processing (almost) from scratch[J]. Journal of Machine Learning Research, 2019, 337:325-338.
[25] GAN L, ZHANG Y. Investigating self-attention network for Chinese word segmentation[J]. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2020, 28:2933-2941.
[26] YU J, JIAN X, XIN H, et al. Joint embeddings of chinese words, characters, and fine-grained subcharacter components[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing, 2017: 286-291.
[27] SUI D, CHEN Y, LIU K, et al. Leverage lexical knowledge for Chinese named entity recognition via collaborative graph network[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, 2019: 3821-3831.[28] CAO P, CHEN Y, LIU K, et al. Adversarial transfer learning for Chinese named entity recognition with self-attention mechanism[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing, 2018: 182-192.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
PDF(1684 KB)
