一种基于span的实体和关系联合抽取方法

计算机工程与科学 ›› 2022, Vol. 44 ›› Issue (03): 502-508.

一种基于span的实体和关系联合抽取方法

余杰1，纪斌1，吴宏明2，任意3，李莎莎1，马俊1 ，吴庆波1

(1.国防科技大学计算机学院，湖南长沙 410073;
2.中央军委装备发展部装备项目管理中心，北京 100034;3.陆军项目管理中心，北京 100071)

收稿日期:2020-11-26 修回日期:2020-12-15 接受日期:2022-03-25 出版日期:2022-03-25 发布日期:2022-03-24
基金资助:

A span-based joint entity and relation extraction method

YU Jie1,JI Bin1,WU Hong-ming2,REN Yi3,LI Sha-sha1,MA Jun1,WU Qing-bo1

(1.College of Computer Science and Technology,National University of Defense Technology,Changsha 410073;
2.Equipment Project Management Center of Equipment Development Department,Central Military Commission,Beijing 100034;
3.Project Management Center of Army,Beijing 100071,China)

Received:2020-11-26 Revised:2020-12-15 Accepted:2022-03-25 Online:2022-03-25 Published:2022-03-24

摘要/Abstract

摘要： 基于span的联合抽取模型在命名实体识别和关系抽取上取得了优异的效果。这些模型将文本span作为候选实体，并将span元组视为候选关系元组。span的语义表示在实体识别和关系分类中共享。然而现有基于span的模型无法很好地捕获这些候选实体和关系的语义，为了解决这些问题，提出了一种融合attention机制的span的联合抽取模型。特别地，attention用于计算相关语义表示，包括span特定特征语义表示和句子上下文的语义表示。实验结果表明，所提出的模型优于以前的模型，并在ACE2005、CoNLL2004和ADE 3个基准数据集上达到了当前最优的结果。

关键词: span, 实体识别, 关系抽取, 联合抽取

Abstract: Span-based joint extraction models have achieved excellent results in named entity recognition and relation extraction. These models regard text spans as candidate entities and span tuples as candidate relation tuples. span semantic representations are shared in both entity recognition and relation extraction, while existing models cannot well capture semantics of these candidate entities and relations. To address these problems, a span-based joint extraction framework with attention-based semantic re- presentations is proposed. Specially, attentions are utilized to calculate semantic representations, includ- ing span-specific and contextual ones. Experiments show that our model outperforms previous systems and achieves state-of-the-art results on ACE2005, CoNLL2004 and ADE.

Key words: span, entity recognition, relation extraction, joint extraction

余杰, 纪斌, 吴宏明, 任意, 李莎莎, 马俊 , 吴庆波. 一种基于span的实体和关系联合抽取方法[J]. 计算机工程与科学, 2022, 44(03): 502-508.

YU Jie, JI Bin, WU Hong-ming, REN Yi, LI Sha-sha, MA Jun, WU Qing-bo. A span-based joint entity and relation extraction method[J]. Computer Engineering & Science, 2022, 44(03): 502-508.

参考文献［23］

［1］	Zheng S,Wang F,Bao H Y,et al.Joint extraction of entities and relations based on a novel tagging scheme ［C］∥Proc of the 55th Annual Meeting of the Association for Computational Linguistics,2017:1227-1236.
［2］	Dixit K,Al-Onaizan Y.Span-level model for relation extraction ［C］∥Proc of the 57th Annual Meeting of the Association for Computational Linguistics,2019:5308-5314.
［3］	Devlin J, Chang M W, Lee K,et al.BERT:Pre-training of deep bidirectional transformers for language understanding ［C］∥Proc of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies,2019:4171-4186.
［4］	Huang Z H,Xu W,Yu K.Bidirectional LSTM-CRF models for sequence tagging ［J］.arXiv:1508.01991,2015.
［5］	Limsopatham N, Collier N.Bidirectional LSTM for named entity recognition in Twitter messages ［C］∥Proc of the 2nd Workshop on Noisy User-generated Text,2016:145-152.
［6］	Zhang X,Wang D. Relation classification via recurrent neural network ［J］.arXiv:1508.01006,2015.
［7］	Zeng D J, Liu K,Lai S W,et al.Relation classification via convolutional deep neural network ［C］∥Proc of the 25th International Conference on Computational Linguistics,2014:2335-2344.
［8］	Patrick V, Emma S, Andrew M. Simultaneously self- attending to all mentions for full-abstract biological relation extraction ［C］∥Proc of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies,2018:872-884.
［9］	Miwa M,Sasaki Y.Modeling joint entity and relation extraction with table representation ［C］∥Proc of the 2014 Confe- rence on Empirical Methods in Natural Language Processing,2014:1858-1869.
［10］	Zhou P,Zheng S C,Xu J M,et al.Joint extraction of multiple relations and entities by using a hybrid neural network ［C］∥Proc of the 16th China National Conference on Chinese Computational Linguistics and Natural Language Processing Based on Naturally Annotated Big Data,2017:135-146.
［11］	Luan Y,He L H,Ostendorf M,et al.Multi-task identification of entities,relations,and coreference for scientific knowledge graph construction ［C］∥Proc of the 2018 Conference on Empirical Methods in Natural Language Proces- sing,2018:3219-3232.
［12］	Lee K,He L H,Lewis M,et al.End-to-end neural corefe- rence resolution ［C］∥Proc of the 2017 Conference on Empirical Methods in Natural Language Processing,2017:188-197.
［13］	Luan Y,Wadden D,He L H,et al.A general framework for information extraction using dynamic span graphs ［C］∥Proc of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies,2019:3036-3046.
［14］	Wadden D,Wennberg U,Luan Y,et al.Entity,relation,and event extraction with contextualized span representations ［C］∥Proc of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing,2019:5783-5788.
［15］	Eberts M,Ulges A.Span-based joint entity and relation extraction with transformer pretraining ［J］.arXiv:1909.07755,2021.
［16］	Bahdanau D,Cho K,Bengio Y.Neural machine translation by jointly learning to align and translate ［C］∥Proc of the 3rd International Conference on Learning Representations,2015:1-15.
［17］	Luong T,Pham H,Christopher D M.Effective approaches to attention-based neural machine translation ［C］∥Proc of the 2015 Conference on Empirical Methods in Natural Language Processing,2015:1412-1421.
［18］	Vaswani A,Shazeer N,Parmar N,et al.Attention is all you need ［C］∥Proc of the 31st International Conference on Neural Information Processing Systems,2017:5998-6008.
［19］	Doddington G R, Mitchell A, Przbocki M, et al.The automatic content extraction (ACE) program-tasks,data,and evaluation ［C］∥Proc of the 4th International Conference on Language Resources and Evaluation,2004:837-840.
［20］	Roth D,Yih W.A linear programming formulation for glo- bal inference in natural language tasks ［C］∥Proc of the 8th Conference on Computational Natural Language Learning,2004:1-8.
［21］	Gurulingappa H,Rajput A M,Roberts A,et al.Development of a benchmark corpus to support the automatic extraction of drug-related adverse effects from medical case reports ［J］.Journal of Biomedical Informatics,2012,45(5):885-892.
［22］	Li X Y,Yin F,Sun Z J,et al.Entity-relation extraction as multi-turn question answering ［C］∥Proc of the 57th Annual Meeting of the Association for Computational Linguistics, 2019:1340-1350.
［23］	Tran T, Kavuluru R.Neural metric learning for fast end-to-end relation extraction ［J］.arXiv:1905.07458,2019.

[1]	喻金平, 朱伟锋, 廖列法. 基于RoBERTa-wwm-BiLSTM-CRF的扶持政策文本实体识别研究[J]. 计算机工程与科学, 2023, 45(08): 1498-1507.
[2]	排日旦·阿布都热依木, 吐尔地·托合提, 艾斯卡尔·艾木都拉, . 基于深度学习的实体关系抽取方法研究[J]. 计算机工程与科学, 2023, 45(05): 895-902.
[3]	李鸿飞, 刘盼雨, 魏勇. 基于自注意力和Lattice-LSTM的军事命名实体识别[J]. 计算机工程与科学, 2021, 43(10): 1848-1855.
[4]	许力, 李建华. 基于BERT和BiLSTM-CRF的生物医学命名实体识别[J]. 计算机工程与科学, 2021, 43(10): 1873-1879.
[5]	谢明鸿, 冉强, 王红斌, . 基于同义词词林和规则的中文远程监督人物关系抽取方法[J]. 计算机工程与科学, 2021, 43(09): 1661-1667.
[6]	仇增辉, 赫明杰, 林正奎. 基于深度学习的网购评论命名实体识别方法[J]. 计算机工程与科学, 2020, 42(12): 2287-2294.
[7]	闫雄, 段跃兴, 张泽华. 采用自注意力机制和CNN融合的实体关系抽取[J]. 计算机工程与科学, 2020, 42(11): 2059-2066.
[8]	肖新凤1,2，李石君2，余伟2，刘杰2，刘倍雄1. 基于改进seq2seq模型的英汉翻译研究[J]. 计算机工程与科学, 2019, 41(07): 1257-1265.
[9]	张玉坤1,2，刘茂福1,2，胡慧君1,2. 基于联合神经网络模型的中文医疗实体分类与关系抽取[J]. 计算机工程与科学, 2019, 41(06): 1110-1118.
[10]	李健龙，王盼卿，韩琪羽. 基于双向LSTM的军事命名实体识别[J]. 计算机工程与科学, 2019, 41(04): 711-718.
[11]	张朝胜1，郭剑毅1,2，线岩团1,2，余正涛1,2，雷春雅1, 王海雄1. 基于条件随机场的英文产品命名实体识别[J]. J4, 2010, 32(6): 115-117.
[12]	施德明林洋港陈恩红. 一种集成NER的文本分类特征选择方法[J]. J4, 2007, 29(11): 152-156.
[13]	张晓艳王挺陈火旺. 基于混合统计模型的汉语命名实体识别方法[J]. J4, 2006, 28(6): 135-139.