Relation extraction method based on entity boundary combination

doi:10.11772/j.issn.1001-9081.2021091747

Journal of Computer Applications ›› 2022, Vol. 42 ›› Issue (6): 1796-1801.DOI: 10.11772/j.issn.1001-9081.2021091747

• The 18th CCF Conference on Web Information Systems and Applications • Previous Articles

Relation extraction method based on entity boundary combination

Hao LI¹^,², Yanping CHEN¹^,²(), Ruixue TANG¹^,², Ruizhang HUANG¹^,², Yongbin QIN¹^,², Guorong WANG¹^,², Xi TAN³

^1.College of Computer Science and Technology，Guizhou University，Guiyang Guizhou 550025，China
^2.State Key Laboratory of Public Big Data （Guizhou University），Guiyang Guizhou 550025，China
^3.Guizhou Qingduo Technology Company Limited，Guiyang Guizhou 550025，China

Received:2021-10-12 Revised:2021-11-11 Accepted:2021-11-17 Online:2022-04-15 Published:2022-06-10
Contact: Yanping CHEN
About author:LI Hao， born in 1996， M. S. candidate. His research interests include natural language processing， relation extraction.
TANG Ruixue， born in 1987， Ph. D. candidate. Her research interests include natural language processing.
HUANG Ruizhang，born in 1979，Ph. D.，professor，Her research interests include data mining， text mining， machine learning，information retrieval.
QIN Yongbin， born in 1980， Ph. D.， professor， His research interests include intelligent computing， machine learning， algorithm design.
WANG Guorong， born in 1995， Ph. D. candidate. Her research interests include natural language processing.
Supported by:
National Natural Science Foundation of China(62066008);Key Project of Science and Technology Foundation of Guizhou Province （Qianke Hejichu ［2020］ 1Z055）

基于实体边界组合的关系抽取方法

李昊¹^,², 陈艳平¹^,²(), 唐瑞雪¹^,², 黄瑞章¹^,², 秦永彬¹^,², 王国蓉¹^,², 谭曦³

^1.贵州大学计算机科学与技术学院, 贵阳 550025
^2.公共大数据国家重点实验室(贵州大学), 贵阳 550025
^3.贵州青朵科技有限公司, 贵阳 550025

通讯作者: 陈艳平
作者简介:李昊（1996—），男，四川成都人，硕士研究生，CCF会员，主要研究方向：自然语言处理、关系抽取
唐瑞雪（1987—），女，贵州贵阳人，博士研究生，主要研究方向：自然语言处理
黄瑞章（1979—），女，天津人，教授，博士，CCF会员，主要研究方向：数据挖掘、文本挖掘、机器学习、信息检索
秦永彬（1980—），男，山东招远人，教授，博士，CCF会员，主要研究方向：智能计算、机器学习、算法设计
王国蓉（1995—），女，贵州瓮安人，博士研究生，主要研究方向：自然语言处理。
基金资助:
国家自然科学基金资助项目(62066008);贵州省科学技术基金重点项目(黔科合基础［2020］1Z055)

Abstract

Abstract:

Relation extraction aims to extract the semantic relationships between entities from the text. As the upper-level task of relation extraction， entity recognition will generate errors and spread them to relation extraction， resulting in cascading errors. Compared with entities， entity boundaries have small granularity and ambiguity， making them easier to recognize. Therefore， a relationship extraction method based on entity boundary combination was proposed to realize relation extraction by skipping the entity and combining the entity boundaries in pairs. Since the boundary performance is higher than the entity performance， the problem of error propagation was alleviated； in addition， the performance was further improved by adding the type features and location features of entities through the feature combination method， which reduced the impact caused by error propagation. Experimental results on ACE 2005 English dataset show that the proposed method outperforms the table-sequence encoders method by 8.61 percentage points on Macro average F1-score.

Key words: relation extraction, entity recognition, cascading error, entity boundary combination, feature combination

摘要：

关系抽取旨在从文本中抽取实体与实体之间的语义关系。作为关系抽取的上层任务，实体识别所产生的错误将扩散至关系抽取，从而导致级联错误。与实体相比，实体边界粒度小且具有二义性，更易识别。因此，提出一种基于实体边界组合的关系抽取方法，通过跳过实体，对实体边界两两组合来进行关系抽取。由于边界性能高于实体性能，所以错误扩散的问题得到了缓解；并且通过特征组合的方法将实体类型特征和位置特征加入模型中，性能得到了进一步提高，再次减轻了错误扩散带来的影响。实验结果表明，所提方法在ACE 2005英文数据集的宏平均F1值优于表格-序列编码器方法8.61个百分点。

关键词: 关系抽取, 实体识别, 级联错误, 实体边界组合, 特征组合

CLC Number:

TP391.1

Hao LI, Yanping CHEN, Ruixue TANG, Ruizhang HUANG, Yongbin QIN, Guorong WANG, Xi TAN. Relation extraction method based on entity boundary combination[J]. Journal of Computer Applications, 2022, 42(6): 1796-1801.

李昊, 陈艳平, 唐瑞雪, 黄瑞章, 秦永彬, 王国蓉, 谭曦. 基于实体边界组合的关系抽取方法[J]. 《计算机应用》唯一官方网站, 2022, 42(6): 1796-1801.

Figures/Tables 5

Fig. 1 Boundary recognition model

Fig. 2 Relation extraction model

Tab. 1 Results of boundary recognition on ACE 2005 dataset unit： %

类型	ACE 2005中文数据集			ACE 2005英文数据集
类型	$P$	$R$	$F 1 M a c r o$	$P$	$R$	$F 1 M a c r o$
开始边界	93.96	95.02	94.49	90.45	92.15	91.29
结束边界	94.46	95.09	94.77	88.16	90.88	89.50
边界组合后	78.85	81.34	80.07	73.37	79.03	76.09

Tab. 1 Results of boundary recognition on ACE 2005 dataset unit： %

类型	ACE 2005中文数据集			ACE 2005英文数据集
类型	$P$	$R$	$F 1 M a c r o$	$P$	$R$	$F 1 M a c r o$
开始边界	93.96	95.02	94.49	90.45	92.15	91.29
结束边界	94.46	95.09	94.77	88.16	90.88	89.50
边界组合后	78.85	81.34	80.07	73.37	79.03	76.09

Tab. 2 Influence of different composite features on performance of start and end boundary on ACE 2005 dataset

特征	开始边界						结束边界
	ACE 2005中文数据集			ACE 2005英文数据集			ACE 2005中文数据集			ACE 2005英文数据集
	$P$	$R$	$F 1 M a c r o$	$P$	$R$	$F 1 M a c r o$	$P$	$R$	$F 1 M a c r o$	$P$	$R$	$F 1 M a c r o$
$E$	71.08	75.12	72.61	59.60	79.64	66.56	72.83	74.63	72.83	58.33	79.05	65.83
$E \| \| Z 1$	81.78	83.56	81.95	64.27	82.01	70.70	82.25	84.35	82.23	63.86	81.35	70.21
$E \| \| Z 2$	92.90	79.62	85.51	66.13	80.50	71.56	93.13	79.92	85.78	65.58	78.23	70.88
$E \| \| Z 1 \| \| Z 2$	92.63	83.53	87.70	79.00	73.98	76.21	92.89	83.95	88.12	77.85	72.65	75.06

Tab. 2 Influence of different composite features on performance of start and end boundary on ACE 2005 dataset

特征	开始边界						结束边界
	ACE 2005中文数据集			ACE 2005英文数据集			ACE 2005中文数据集			ACE 2005英文数据集
	$P$	$R$	$F 1 M a c r o$	$P$	$R$	$F 1 M a c r o$	$P$	$R$	$F 1 M a c r o$	$P$	$R$	$F 1 M a c r o$
$E$	71.08	75.12	72.61	59.60	79.64	66.56	72.83	74.63	72.83	58.33	79.05	65.83
$E \| \| Z 1$	81.78	83.56	81.95	64.27	82.01	70.70	82.25	84.35	82.23	63.86	81.35	70.21
$E \| \| Z 2$	92.90	79.62	85.51	66.13	80.50	71.56	93.13	79.92	85.78	65.58	78.23	70.88
$E \| \| Z 1 \| \| Z 2$	92.63	83.53	87.70	79.00	73.98	76.21	92.89	83.95	88.12	77.85	72.65	75.06

Tab. 3 Performance comparison of different methods

方法	Entity			Relation
方法	$P$	$R$	$F 1 M a c r o$	$P$	$R$	$F 1 M a c r o$
文献［17］方法	85.2	76.9	80.8	65.4	39.8	49.5
文献［12］方法	82.9	83.9	83.4	57.2	54.0	55.6
文献［18］方法	—	—	83.6	—	—	57.5
文献［15］方法	84.0	81.3	82.6	55.5	51.8	53.6
文献［19］方法	84.7	84.9	84.8	64.8	56.2	60.2
文献［6］方法	—	—	89.5	—	—	67.6
本文方法+entity	73.37	79.03	76.09	60.36	67.85	63.62
本文方法+boundary	90.45	92.15	91.29	79.00	73.98	76.21

Tab. 3 Performance comparison of different methods

方法	Entity			Relation
方法	$P$	$R$	$F 1 M a c r o$	$P$	$R$	$F 1 M a c r o$
文献［17］方法	85.2	76.9	80.8	65.4	39.8	49.5
文献［12］方法	82.9	83.9	83.4	57.2	54.0	55.6
文献［18］方法	—	—	83.6	—	—	57.5
文献［15］方法	84.0	81.3	82.6	55.5	51.8	53.6
文献［19］方法	84.7	84.9	84.8	64.8	56.2	60.2
文献［6］方法	—	—	89.5	—	—	67.6
本文方法+entity	73.37	79.03	76.09	60.36	67.85	63.62
本文方法+boundary	90.45	92.15	91.29	79.00	73.98	76.21

References 19

1	刘峤，李杨，段宏，等.知识图谱构建技术综述［J］. 计算机研究与发展，2016，53（3）：582-600. 10.7544/issn1000-1239.2016.20148228
	LIU Q， LI Y， DUAN H， et al. Knowledge graph construction techniques［J］. Journal of Computer Research and Development， 2016， 53（3）： 582-600. 10.7544/issn1000-1239.2016.20148228
2	徐健，张智雄，吴振新.实体关系抽取的技术方法综述［J］. 现代图书情报技术，2008，24（8）：18-23. 10.3969/j.issn.1003-3513.2008.08.004
	XU J， ZHANG Z X， WU Z X. Review on techniques of entity relation extraction［J］. New Technology of Library and Information Service， 2008， 24（8）： 18-23. 10.3969/j.issn.1003-3513.2008.08.004
3	CHEN Y P， WU Y F， QIN Y B， et al. Recognizing nested named entity based on the neural network boundary assembling model［J］. IEEE Intelligent Systems， 2020， 35（1）： 74-81. 10.1109/mis.2019.2952334
4	CHEN Y P， WANG G R， ZHENG Q H， et al. A set space model to capture structural information of a sentence［J］. IEEE Access， 2019， 7：142515-142530. 10.1109/access.2019.2944559
5	CHEN Y P， WANG K， YANG W Z， et al. A multi-channel deep neural network for relation extraction［J］. IEEE Access， 2020， 8： 13195-13203. 10.1109/access.2020.2966303
6	WANG J， LU W. Two are better than one： joint entity and relation extraction with table-sequence encoders［C］// Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing. Stroudsburg， PA： ACL， 2020： 1706-1721. 10.18653/v1/2020.emnlp-main.133
7	鄂海红，张文静，肖思琪，等. 深度学习实体关系抽取研究综述［J］. 软件学报， 2019， 30（6）：1793-1818. 10.13328/j.cnki.jos.005817
	E H H， ZHANG W J， XIAO S Q， et al. Survey of entity relationship extraction based on deep learning［J］. Journal of Software， 2019， 30（6）：1793-1818. 10.13328/j.cnki.jos.005817
8	HASHIMOTO K， MIWA M， TSURUOKA Y， et al. Simple customization of recursive neural networks for semantic relation classification［C］// Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing. Stroudsburg， PA： ACL， 2013： 1372-1376. 10.3115/v1/d14-1163
9	ZENG D J， LIU K， LAI S W， et al. Relation classification via convolutional deep neural network［C］// Proceedings of the 25th International Conference on Computational Linguistics： Technical Papers. Stroudsburg， PA： ACL， 2014： 2335-2344.
10	WANG L L， CAO Z， DE MELO G， et al. Relation classification via multi-level attention CNNs［C］// Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics （Volume 1： Long Papers）. Stroudsburg， PA： ACL， 2016： 1298-1307. 10.18653/v1/p16-1123
11	LI F， ZHANG M S， FU G H， et al. A Bi-LSTM-RNN model for relation classification using low-cost sequence features［EB/OL］. ［2021-10-28］.. 10.7753/ijsea1009.1006
12	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 （Volume 1： Long Papers）. Stroudsburg， PA： ACL， 2016： 1105-1116. 10.18653/v1/p16-1105
13	LI F， ZHANG M S， FU G H， et al. A neural joint model for extracting bacteria and their locations［C］// Proceedings of the 2017 Pacific-Asia Conference on Knowledge Discovery and Data Mining， LNCS 10235/LNAI 10235. Cham： Springer， 2017： 15-26.
14	KATIYAR A， CARDIE C. Investigating LSTMs for joint extraction of opinion entities and relations［C］// Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics （Volume 1： Long Papers）. Stroudsburg， PA： ACL， 2016： 919-929. 10.18653/v1/p16-1087
15	KATIYAR A， CARDIE C. Going out on a limb： joint extraction of entity mentions and relations without dependency trees［C］// Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics （Volume 1： Long Papers）. Stroudsburg， PA： ACL， 2017： 917-928. 10.18653/v1/p17-1085
16	ZHENG S C， WANG F， BAO H Y， 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 Computational Linguistics （Volume 1： Long Papers）. Stroudsburg， PA： ACL， 2017： 1227-1236. 10.18653/v1/p17-1113
17	LI Q， JI H. Incremental joint extraction of entity mentions and relations［C］// Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics （Volume 1： Long Papers）. Stroudsburg， PA： Association for Computational Linguistics， 2014： 402-412. 10.3115/v1/p14-1038
18	ZHANG M S， ZHANG Y， FU G H. End-to-end neural relation extraction with global optimization［C］// Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing. Stroudsburg， PA： ACL， 2017： 1730-1740. 10.18653/v1/d17-1182
19	LI X Y， YIN F， SUN Z J， et al. Entity-relation extraction as multi-turn question answering［C］// Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. Stroudsburg， PA： ACL， 2019： 1340-1350. 10.18653/v1/p19-1129

[1]	Yi ZHANG, Shuangsheng WANG, Bin HE, Peiming YE, Keqiang LI. Named entity recognition method of elementary mathematical text based on BERT [J]. Journal of Computer Applications, 2022, 42(2): 433-439.
[2]	Xiaopeng WANG, Yuanyuan SUN, Hongfei LIN. Encoding-decoding relationship extraction model based on criminal Electra [J]. Journal of Computer Applications, 2022, 42(1): 87-93.
[3]	LIU Yaxuan, ZHONG Yong. Joint extraction method of entities and relations based on subject attention [J]. Journal of Computer Applications, 2021, 41(9): 2517-2522.
[4]	WU Guoliang, XU Jining. Chinese emergency event extraction method based on named entity recognition task feedback enhancement [J]. Journal of Computer Applications, 2021, 41(7): 1891-1896.
[5]	WANG Zhujun, WANG Shi, LI Xueqing, ZHU Junwu. Review of event causality extraction based on deep learning [J]. Journal of Computer Applications, 2021, 41(5): 1247-1255.
[6]	CUI Bowen, JIN Tao, WANG Jianmin. Overview of information extraction of free-text electronic medical records [J]. Journal of Computer Applications, 2021, 41(4): 1055-1063.
[7]	WANG Xiaoxia, QIAN Xuezhong, SONG Wei. Relation extraction model via attention-based graph convolutional network [J]. Journal of Computer Applications, 2021, 41(2): 350-356.
[8]	XU Li, LI Jianhua. Biomedical named entity recognition with graph network based on syntactic dependency parsing [J]. Journal of Computer Applications, 2021, 41(2): 357-362.
[9]	Bowen YAO, Biqing ZENG, Jian CAI, Meirong DING. Chinese character relation extraction model based on pre-training and multi-level information [J]. Journal of Computer Applications, 2021, 41(12): 3637-3644.
[10]	WU Xiaoping, ZHANG Qiang, ZHAO Fang, JIAO Lin. Entity relation extraction method for guidelines of cardiovascular disease based on bidirectional encoder representation from transformers [J]. Journal of Computer Applications, 2021, 41(1): 145-149.
[11]	ZHANG Xinyi, FENG Shimin, DING Enjie. Entity recognition and relation extraction model for coal mine [J]. Journal of Computer Applications, 2020, 40(8): 2182-2188.
[12]	HU Tiantian, DAN Yabo, HU Jie, LI Xiang, LI Shaobo. News named entity recognition and sentiment classification based on attention-based bi-directional long short-term memory neural network and conditional random field [J]. Journal of Computer Applications, 2020, 40(7): 1879-1883.
[13]	XUE Lu, SONG Wei. Relation extraction method based on dynamic label [J]. Journal of Computer Applications, 2020, 40(6): 1601-1606.
[14]	Yue WANG, Mengxuan WANG, Sheng ZHANG, Wen DU. Alarm text named entity recognition based on BERT [J]. Journal of Computer Applications, 2020, 40(2): 535-540.
[15]	CHEN Jiafeng, TENG Chong. Joint entity and relation extraction model based on reinforcement learning [J]. Journal of Computer Applications, 2019, 39(7): 1918-1924.

Relation extraction method based on entity boundary combination

基于实体边界组合的关系抽取方法

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 5

References 19

Related Articles 15

Recommended Articles

Metrics