基于分割注意力与边界感知的中文嵌套命名实体识别算法

doi:10.11896/jsjkx.211100257

摘要/Abstract

摘要： 由于中文文本缺少天然分隔符,中文嵌套命名实体识别(Chinese Nested Named Entity Recognition,CNNER)任务极具挑战性,而嵌套结构的复杂性和多变性更增添了任务的难度。文中针对CNNER任务提出了一种新型边界感知层叠神经网络模型( Boundary-aware Layered Nerual Model,BLNM)。首先通过构建了一个分割注意力网络来捕获潜在的分词信息和相邻字符之间的语义关系,以增强字符表示;然后通过动态堆叠扁平命名实体识别层的网络,由小粒度到大粒度逐层识别嵌套实体;最后为了利用被预测实体的边界信息和位置信息,构建了一个边界生成式模块,用于连接相邻的扁平命名实体识别层以及缓解错误传递问题。基于ACE 2005中文嵌套命名实体数据集的实验结果表明,该模型具有较好的性能。

关键词: 中文嵌套命名实体识别, 分割注意力, 边界生成式, 层叠神经网络

Abstract: Chinese nested named entity recognition(CNNER) is a challenging task due to the absence of natural delimiters in Chinese and the complexity of the nested structure.In this paper,we propose a novel boundary-aware layered neural model(BLNM) with segmentation attention for the CNNER task.To exploit some semantic relation among adjacent characters,we first design a segmentation attention network to capture the potential word information and enhance character representation.Next,we model the nested structure with dynamically stacked Flat NER networks to detect entities in an inner to outer manner.We also design a boundary generative module to connect adjacent Flat NER layers,which can mark the boundary and position of detected entities and greatly alleviate the error propagation problem.Experiment results on ACE 2005 Chinese nested NE dataset show that the proposed model achieves superior performance than the state-of-the-art methods.

Key words: Chinese nested named entity recognition, Segmentation attention, Boundary generative, Layered neural network

中图分类号:

TP391.1

张汝佳, 代璐, 郭鹏, 王邦. 基于分割注意力与边界感知的中文嵌套命名实体识别算法[J]. 计算机科学, 2023, 50(1): 213-220. https://doi.org/10.11896/jsjkx.211100257

ZHANG Rujia, DAI Lu, GUO Peng, WANG Bang. Chinese Nested Named Entity Recognition Algorithm Based on Segmentation Attention andBoundary-aware[J]. Computer Science, 2023, 50(1): 213-220. https://doi.org/10.11896/jsjkx.211100257

参考文献

[1]GUPTA N,SINGH S,ROTH D.Entity linking via joint encoding of types,descriptions,and con-text[C]//Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing.Denmark:ACL,2017:2681-2690.
[2]JI Z,SUN A,CONG G,et al.Joint recognition and linking of fine-grained locations from tweets[C]//Proceedings of the 25th International Conference on World Wide Web.Montréal:WWW,2016:1271-1281.
[3]LIN Y,SHEN S,LIU Z,et al.Neural relation extraction with selective attention over in-stances[C]//Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics.Germany:ACL,2016:2124-2133.
[4]ZHENG S,WANG F,BAO H,et al.Joint extraction of entities and relations based on a novel tagging scheme[C]//Proceedings of the 55th Annual Meeting of the Association for Computa-tional Linguistics.Vancouver:ACL,2017:1227-1236.
[5]CHANG K W,SAMDANI R,ROTH D.A constrained latent variable model for coreference resolution [C]//Proceedings of the 2013 Conference on Empirical Methodsin Natural Language Processing.Seattle:EMNLP,2013:601-612.
[6]SHEN D,ZHANG J,ZHOU G,et al.Effective adaptation of hidden markov model-based named entity recognizer for biome-dical domain[C]//Proceedings of the ACL 2003 Workshop on Natural Language Processing in Biomedicine.Japan:ACL,2003:49-56.
[7]XIA C,ZHANG C,YANG T,et al.Multi-grained named entity recognition[C]//Proceedings of the 57th Annual Meeting of the Association for Compu-tational Linguistics.Italy:ACL,2019:1430-1440.
[8]JU M,MIWA M,ANANIADOU S.A neural layered model for nested named entity recognition[C]// Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics.New Orleans:ACL,2018:1446-1459.
[9]LI H,XU H,QIAN L,et al.Multi-layer Joint Learning of Chinese Nested Named Entity Recognition Based on Self-attention Mechanism[C]//Proceedings of the 9th CCF International Conference on Natural Language Processing and Chinese Computing.Cham:Springer International Publishing,2020:144-155.
[10]KURU O,CAN O A,YURET D.CharNER:Character-levelnamed entity recognition[C]//Proceedings of COLING 2016,the 26th International Conference on Computational Linguistics:Technical Papers.Osaka:COLING,2016:911-921.
[11]TRAN Q,MACKINLAY A,YEPES A J.Named entity recognition with stack residual lstm and trainable bias decoding[J].arXiv:1706.07598,2017.
[12]GRIDACH M.Character-level neural network for biomedicalnamed entity recognition[J].Journal of biomedical informatics,2017,70:85-91.
[13]EBERTS M,ULGES A.Span-based joint entity and relation extraction with transformer pre-training[J].arXiv:1909.07755,2019.
[14]HUANG Z,XU W,YU K.Bidirectional LSTM-CRF models for sequence tagging[J].arXiv:1508.01991,2015.
[15]LIU L,SHANG J,REN X,et al.Empower sequence labeling with task-aware neural language model[C]//Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence.New Orleans:AAAI Press,2018:5253-5260.
[16]LUAN Y,WADDEN D,HE L,et al.A general framework for information extraction using dynamic span graphs[C]//Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics.Minnesota:ACL,2019:3036-3046.
[17]DONG C,ZHANG J,ZONG C,et al.Character-based LSTM-CRF with radical-level features for Chinese named entity recognition[C]//International Conference on Computer Processing of Oriental Languages.Cham:Springer International Publishing,2016:239-250.
[18]ZHANG Y,YANG J.Chinese NER using lattice LSTM[C]//Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics.Melbourne:ACL,2018:1554-1564.
[19]LIU W,XU T,XU Q,et al.An encoding strategy based word-character LSTM for Chinese NER[C]//Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics.Minneapolis:ACL,2019:2379-2389.
[20]WU Y,JIANG M,LEI J,et al.Named entity recognition in Chinese clinical text using deep neural network[J].Studies in health technology and informatics,2015,216:624-628.
[21]GUI T,ZOU Y,ZHANG Q,et al.A Lexicon-Based Graph Neural Network forChinese NER[C]//Proceedings of the 2019 Conference on Empirical Methods in Natural Language Proces-sing and the 9th International Joint Conference on Natural Language Processing.Hong Kong:ACL,2019:1040-1050.
[22]LI X,YAN H,QIU X,et al.FLAT:Chinese NER Using Flat-Lattice Transformer[C]//Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics.Online:ACL,2020:6836-6842.
[23]MENGGE X,YU B,LIU T,et al.Porous Lattice Transformer Encoder for Chinese NER[C]//Proceedings of the 28th International Conference on Computational Linguistics.Barcelona:International Committee on Computational Linguistics,2020:3831-3841.
[24]GUI T,MA R,ZHANG Q,et al.CNN-Based Chinese NER with Lexicon Rethinking[C]//Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence Main track.Macao:IJCAI,2019:4982-4988.
[25]SUI D,CHEN Y,LIU K,et al.Leverage lexical knowledge for Chinese named entity recognition via collaborative graph network[C]//Proceedings of the 2019 Conference on Empirical Methods in Natural Language.Hong Kong:EMNLP,2019:3830-3840.
[26]LI J H,CHEN M M,WANG H J,et al.Chinese Named Entity Recognition Method Based on ALBERT-BGRU-CRF[J].Computer Engineering,2022,48(6):89-94,106.
[27]ZHONG S S,CHEN X,ZHAO M H,et al.Incorporating word-set attention into Chinese named entity recognition Method[J].Journal of Jilin University(Engineering and Technology Edition),2022,52(5):1098-1105.
[28]GUO X R,LUO P,WANG W L.Chinese named entity recognition based on Transformer encoder[J].Journal of Jilin University(Engineering and Technology Edition),2021,51(3):989-995.
[29]SI Y C,GUAN Y Q.Chinese Named Entity Recognition Model Based on Transformer Encoder[J].Computer Engineering,2022,48(7):66-72.
[30]HU X B,YU X Q,LI S M,et al.Chinese Named Entity Recognition Based on Knowledge Enhancement[J].Computer Engineering,2021,47(11):84-92.
[31]FU C,ZHAO Y,FU G.Exploiting entity-level morphology to Chinese nested named entity recognition[J].International Journal on Asian Language Processing,2012,22(1):33-48.
[32]ZHOU G,ZHANG J,SU J,et al.Recognizing names in biome-dical texts:a machine learning approach[J].Bioinformatics,2004,20(7):1178-1190.
[33]ZHOU G D.Recognizing names in biomedical texts using mutual information independence model and SVM plus sigmoid[C]//Proceedings of the International Joint Workshop on Natural Language Processing in Bio-medicine and its Applications.Geneva,Switzerland:COLING,2004:1-7.
[34]FU C,FU G.Morpheme-based chinese nested named entity recognition[C]//Proceedings of the 2011 Eighth International Conference on Fuzzy Systems and Knowledge Discovery.Shanghai:FSKD,2011:1221-1225.
[35]LAMPLE G,BALLESTEROS M,SUBRAMANIAN S,et al.Neural architectures for named entity recognition[C]//Procee-dings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics.San Diego:NAACL,2016:260-270.
[36]LAFFERTY J,MCCALLUM A,PEREIRA F C N.Conditional random fields:Probabilistic models for segmenting and labeling sequence data[C]//Proceedings of the 8th International Confe-rence on Machine Learning.Evanston:ICML,1991:282-289.
[37]VITERBI A.Error bounds for convolutional codes and an asymptotically optimum decoding algorithm [C]//Proceedings of IEEE Transactions on Information Theory.IEEE,1967:260-269.
[38]VASWANI A,SHAZEER N,PARMAR N,et al.Attention isall you need[J].arXiv:1706.03762,2017.
[39]DODDINGTON G R,MITCHELL A,PRZYBOCKI M A,et al.The automatic content extraction(ace) program-tasks,data,and evaluation[C]//Proceedings of the Fourth International Confe-rence on Language Resources and Evaluation.Portugal:Euro-pean Language Resources Association,2004:837-840.
[40]PASZKE A,GROSS S,MASSA F,et al.Pytorch:An imperative style,high-performance deep learning library[J].arXiv:1912.01703,2019.

相关文章 15

[1]	于娟, 张晨. 基于Kernel-XGBoost的跨语言术语对齐方法 Cross-lingual Term Alignment with Kernel-XGBoost 计算机科学, 2022, 49(11A): 211000111-6. https://doi.org/10.11896/jsjkx.211000111
[2]	朱若尘, 杨长春, 张登辉. EGOS-DST:对话现象感知和模式引导的一步对话状态追踪算法 EGOS-DST:Efficient Schema-guided Approach to One-step Dialogue State Tracking for Diverse Expressions 计算机科学, 2022, 49(11A): 210900246-7. https://doi.org/10.11896/jsjkx.210900246
[3]	史伟, 付月. 突发事件中网络评论的情感-主题随时间的演变研究 Study on Evolution of Sentiment-Topic of Internet Reviews with Time in Emergencies 计算机科学, 2022, 49(11A): 211000193-6. https://doi.org/10.11896/jsjkx.211000193
[4]	郭军成, 万刚, 胡欣杰, 王帅, 严发宝. 基于少样本的太阳射电爆发事件检测研究 Study on Solar Radio Burst Event Detection Based on Transfer Learning 计算机科学, 2022, 49(11A): 210900198-7. https://doi.org/10.11896/jsjkx.210900198
[5]	张斌, 刘长红, 曾胜, 揭安全. 基于时空图卷积网络的语音驱动个人风格手势生成方法 Speech-driven Personal Style Gesture Generation Method Based on Spatio-Temporal GraphConvolutional Networks 计算机科学, 2022, 49(11A): 210900094-5. https://doi.org/10.11896/jsjkx.210900094
[6]	吴子仪, 李邵梅, 姜梦函, 张建朋. 基于自注意力模型的本体对齐方法 Ontology Alignment Method Based on Self-attention 计算机科学, 2022, 49(9): 215-220. https://doi.org/10.11896/jsjkx.210700190
[7]	郭雨欣, 陈秀宏. 融合BERT词嵌入表示和主题信息增强的自动摘要模型 Automatic Summarization Model Combining BERT Word Embedding Representation and Topic Information Enhancement 计算机科学, 2022, 49(6): 313-318. https://doi.org/10.11896/jsjkx.210400101
[8]	黄少滨, 孙雪薇, 李熔盛. 基于跨句上下文信息的神经网络关系分类方法 Relation Classification Method Based on Cross-sentence Contextual Information for Neural Network 计算机科学, 2022, 49(6A): 119-124. https://doi.org/10.11896/jsjkx.210600150
[9]	缪峰, 王萍, 李太勇. 基于事件动作方向的隐式因果关系抽取方法 Implicit Causality Extraction Method Based on Event Action Direction 计算机科学, 2022, 49(3): 276-280. https://doi.org/10.11896/jsjkx.211100249
[10]	肖康, 周夏冰, 王中卿, 段湘煜, 周国栋, 张民. 基于产品建模的评论问题生成研究 Review Question Generation Based on Product Profile 计算机科学, 2022, 49(2): 272-278. https://doi.org/10.11896/jsjkx.201200208
[11]	马建红, 张烔. 面向企业工程问题的专家推荐算法 Expert Recommendation Algorithm for Enterprise Engineering Problems 计算机科学, 2022, 49(1): 159-165. https://doi.org/10.11896/jsjkx.201200227
[12]	袁景凌, 丁远远, 盛德明, 李琳. 基于视觉方面注意力的图像文本情感分析模型 Image-Text Sentiment Analysis Model Based on Visual Aspect Attention 计算机科学, 2022, 49(1): 219-224. https://doi.org/10.11896/jsjkx.201000074
[13]	刘凯, 张宏军, 陈飞琼. 基于领域适应嵌入的军事命名实体识别 Name Entity Recognition for Military Based on Domain Adaptive Embedding 计算机科学, 2022, 49(1): 292-297. https://doi.org/10.11896/jsjkx.201100007
[14]	邹傲, 郝文宁, 靳大尉, 陈刚, 田媛. 基于预训练和深度哈希的大规模文本检索研究 Study on Text Retrieval Based on Pre-training and Deep Hash 计算机科学, 2021, 48(11): 300-306. https://doi.org/10.11896/jsjkx.210300266
[15]	俞亮, 魏永丰, 罗国亮, 邬昌兴. 基于知识蒸馏的隐式篇章关系识别 Knowledge Distillation Based Implicit Discourse Relation Recognition 计算机科学, 2021, 48(11): 319-326. https://doi.org/10.11896/jsjkx.201000099

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed