由于中文词语缺乏明确的边界和大小写特征,单字在不同词语下的意思也不尽相同,较于英文,中文命名实体识别显得更加困难。该文利用词向量的特点,提出了一种用于深度学习框架的字词联合方法,将字特征和词特征统一地结合起来,它弥补了词特征分词错误蔓延和字典稀疏的不足,也改善了字特征因固定窗口大小导致的上下文缺失。在词特征中加入词性信息后,进一步提高了系统的性能。在1998年《人民日报》语料上的实验结果表明,该方法达到了良好的效果,在地名、人名、机构名识别任务上分别提高1.6%、8%、3%,加入词性特征的字词联合方法的F1值可以达到96.8%、94.6%、88.6%。
Abstract
Chinese NER is challenged by the implicit word boundary, lack of capitalization, and the polysemy of a single character in different words. This paper proposes a novel character-word joint encoding method in a deep learning framework for Chinese NER. It decreases the effect of improper word segmentation and sparse word dictionary in word-only embedding, while improves the results in character-only embedding of context missing. Experiments on the corpus of the Chinese Peoples' Daily Newspaper in 1998 demonstrates a good results: at least 1.6%, 8% and 3% improvements, respectively, in location, person and organization recognition tasks compared with character or word features; and 96.8%, 94.6%, 88.6% in F1, respectively, on location, person and organization recognition tasks if integrated with part of speech feature.
关键词
命名实体识别 /
深度学习 /
神经网络 /
机器学习 /
词性
{{custom_keyword}} /
Key words
named entity recognition /
deep learning /
neural network /
machine learning /
POS
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] Volk M, Clematide S. Learn-filter-apply-forget. mixed approaches to named entity recognition[C]//Proceedings of NLDB, 2001(1): 153-163.
[2] Finkel J R, Grenager T, Manning C. Incorporating non-local information into information extraction systems by gibbs sampling[C]//Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics. Association for Computational Linguistics, 2005: 363-370.
[3] Bikel D M, Schwartz R, Weischedel R M. An algorithm that learns what's in a name[J]. Machine learning, 1999, 34(1-3): 211-231.
[4] Borthwick A. A maximum entropy approach to named entity recognition[D]. New York University, 1999.
[5] McCallum A, Li W. Early results for named entity recognition with conditional random fields, feature induction and web-enhanced lexicons[C]//Proceedings of the 7th conference on natural language learning at HLT-NAACL 2003-Volume 4. Association for Computational Linguistics, 2003: 188-191.
[6] Zhou G D, Su J. Named entity recognition using an HMM-based chunk tagger[C]//Proceedings of the 40th Annual Meeting on Association for Computational Linguistics. Association for Computational Linguistics, 2002: 473-480.
[7] Lafferty J, McCallum A, Pereira F C N. Conditional random fields: probabilistic models for segmenting and labeling sequence data[C]//Proceedings of 18th Internationl conference on Nachine Learning.Williamstoun: ICML,2001: 282-289.
[8] 赵军. 命名实体识别、排歧和跨语言关联[J]. 中文信息学报, 2009, 23(2): 3-17.
[9] 陈钰枫, 宗成庆, 苏克毅. 汉英双语命名实体识别与对齐的交互式方法[J]. 计算机学报, 2011,34(9): 1688-1696.
[10] 邱泉清, 苗夺谦, 张志飞. 中文微博命名实体识别[J]. 计算机科学, 2013, 40(6): 196-198.
[11] Mikolov T, Yih W, Zweig G. Linguistic regularities in continuous space word representations[C]//Proceedings of HLT-NAACL 2013.ACL,2013: 746-751.
[12] Collobert R, Weston J, Bottou L, et al. Natural language processing (almost) from scratch[J]. The Journal of Machine Learning Research, 2011,12: 2493-2537.
[13] Wu Y, Zhao J, Xu B, et al. Chinese named entity recognition based on multiple features[C]//Proceedings of the conference on human language technology and empirical methods in natural language processing. Association for Computational Linguistics, 2005: 427-434.
[14] Klein D, Smarr J, Nguyen H, et al. Named entity recognition with character-level models[C]//Proceedings of the seventh conference on natural language learning at HLT-NAACL 2003-Volume 4. Association for Computational Linguistics, 2003: 180-183.
[15] Zheng X, Chen H, Xu T. Deep learning for Chinese word segmentation and POS tagging[C]//Proceedings of EMNLP, 2013: 647-657.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
基金
国家重点基础研究发展计划(“973”计划)(2014CB340401);国家自然基金(61232010,61433014,61425016,61472401,61203298);中国科学院青年创新促进会优秀会员项目(20144310,2016102);泰山学者工程专项经费(ts201511082)
{{custom_fund}}
PDF(3348 KB)
