Forest-based entity-relation joint extraction model

doi:10.11772/j.issn.1001-9081.2022091419

Journal of Computer Applications ›› 2023, Vol. 43 ›› Issue (9): 2700-2706.DOI: 10.11772/j.issn.1001-9081.2022091419

• 2022 10th CCF Conference on Big Data • Previous Articles Next Articles

Forest-based entity-relation joint extraction model

Xuanli WANG¹^,², Xiaolong JIN¹^,²(), Zhongni HOU¹^,², Huaming LIAO¹^,², Jin ZHANG¹^,²

^1.Key Laboratory of Network Data Science and Technology，Chinese Academy of Sciences （Institute of Computing Technology，Chinese Academy of Sciences），Beijing 100190，China
^2.University of Chinese Academy of Sciences，Beijing 100049，China

Received:2022-09-21 Revised:2022-11-07 Accepted:2022-11-14 Online:2023-02-24 Published:2023-09-10
Contact: Xiaolong JIN
About author:WANG Xuanli， born in 1996， M. S. Her research interests include knowledge graph.
HOU Zhongni， born in 1996， Ph. D.， candidate. Her research interests include knowledge graph， event logic graph.
LIAO Huaming， born in 1972， Ph. D.， associate professor. Her research interests include big data application， information retrieval， distributed data processing.
ZHANG Jin， born in 1978， Ph. D.， senior engineer. His research interests include public opinion analysis， natural language processing， big data processing.

基于森林的实体关系联合抽取模型

王炫力¹^,², 靳小龙¹^,²(), 侯中妮¹^,², 廖华明¹^,², 张瑾¹^,²

^1.中国科学院网络数据科学与技术重点实验室（中国科学院计算技术研究所），北京 100190
^2.中国科学院大学，北京 100049

通讯作者: 靳小龙
作者简介:王炫力（1996—），女，安徽亳州人，硕士，CCF会员，主要研究方向：知识图谱
侯中妮（1996—），女，山东青岛人，博士研究生，主要研究方向：知识图谱、事理图谱
廖华明（1972—），女，四川成都人，副教授，博士，主要研究方向：大数据应用、信息检索、分布式数据处理
张瑾（1978—），男，湖北应城人，高级工程师，博士，主要研究方向：舆情分析、自然语言处理、大数据处理。

Abstract

Abstract:

Nested entities pose a challenge to the task of entity-relation joint extraction. The existing joint extraction models have the problems of generating a large number of negative examples and high complexity when dealing with nested entities. In addition， the interference of nested entities on triplet prediction is not considered by these models. To solve these problems， a forest-based entity-relation joint extraction method was proposed， named EF2LTF （Entity Forest to Layering Triple Forest）. In EF2LTF， a two-stage joint training framework was adopted. Firstly， through the generation of an entity forest， different entities within specific nested entities were identified flexibly. Then， the identified nested entities and their hierarchical structures were combined to generate a hierarchical triplet forest. Experimental results on four benchmark datasets show that EF2LTF outperforms methods such as joint entity and relation extraction with Set Prediction Network （SPN） model， joint extraction model for entities and relations based on Span — SpERT （Span-based Entity and Relation Transformer） and Dynamic Graph Information Extraction ++ （DyGIE++）^{on F1 score. It is verified that the proposed method not only enhances the recognition ability of nested entities， but also enhances the ability to distinguish nested entities when constructing triples， thereby improving the joint extraction performance of entities and relations.}

Key words: entity-relation joint extraction, triplet generation, nested entity, layering prediction, entity forest

摘要：

嵌套实体对实体关系联合提取任务提出了挑战。现有的联合抽取模型在处理嵌套实体时存在产生大量负例且复杂度高的问题，此外未考虑嵌套实体对三元组预测的干扰。针对以上问题，提出一种基于森林的实体关系联合抽取方法——EF2LTF（Entity Forest to Layering Triple Forest）。EF2LTF采用了一个两阶段的联合训练框架，首先通过生成实体森林灵活地在嵌套实体内部识别不同的实体；然后结合已识别出的嵌套实体及其层次结构生成分层的三元组森林。在四个标准数据集上的实验结果表明，与基于集合预测网络的SPN（Set Prediction Network）模型、基于跨度的实体关系联合抽取模型SpERT（Span-based Entity and Relation Transformer）和动态图增强信息抽取（DyGIE++）等方法相比，所提方法取得了最优的F1值。说明所提方法既增强了嵌套实体的识别能力，也增强了构建三元组时对嵌套实体的分辨能力，从而提升了实体与关系的联合抽取性能。

关键词: 实体关系联合抽取, 三元组生成, 嵌套实体, 分层预测, 实体森林

CLC Number:

TP391.1

Xuanli WANG, Xiaolong JIN, Zhongni HOU, Huaming LIAO, Jin ZHANG. Forest-based entity-relation joint extraction model[J]. Journal of Computer Applications, 2023, 43(9): 2700-2706.

王炫力, 靳小龙, 侯中妮, 廖华明, 张瑾. 基于森林的实体关系联合抽取模型[J]. 《计算机应用》唯一官方网站, 2023, 43(9): 2700-2706.

Figures/Tables 7

References 29

1	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
2	WANG Y C， YU B W， ZHANG Y Y， et al. TPLinker： single-stage joint extraction of entities and relations through token pair linking［C］// Proceedings of the 28th International Conference on Computational Linguistics. Stroudsburg， PA： ACL， 2020： 1572-1582. 10.18653/v1/2020.coling-main.138
3	LUAN Y， WADDEN D， HE L H， 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： Human Language Technologies， Volume 1 （Long and Short Papers）. Stroudsburg， PA： ACL， 2019： 3036-3046. 10.18653/v1/n19-1308
4	WADDEN D， WENNBERG U， LUAN Y， et al. Entity， relation， and event extraction with contextualized span representations［C］// Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing. Stroudsburg， PA： ACL， 2019： 5784-5789. 10.18653/v1/d19-1585
5	EBERTS M， ULGES A. Span-based joint entity and relation extraction with Transformer pre-training［C］// Proceedings of the 24th European Conference on Artificial Intelligence. Amsterdam： IOS Press， 2020： 2006-2013. 10.18653/v1/2021.eacl-main.319
6	GARDENT C， SHIMORINA A， NARAYAN S， et al. Creating training corpora for NLG micro-planners［C］// Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics （Volume 1： Long Papers）. Stroudsburg， PA： ACL， 2017： 179-188. 10.18653/v1/p17-1017
7	RIEDEL S， YAO L M， McCALLUM A. Modeling relations and their mentions without labeled text［C］// Proceedings of the 2010 Joint European Conference on Machine Learning and Knowledge Discovery in Databases， LNCS 6323. Berlin： Springer， 2010： 148-163. 10.5715/jnlp.4.3_1
8	LUAN Y， HE L H， OSTENDORF M， et al. Multi-task identification of entities， relations， and coreference for scientific knowledge graph construction［C］// Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. Stroudsburg， PA： ACL， 2018： 3219-3232. 10.18653/v1/d18-1360
9	WALKER C， STRASSEL S， MEDERO J， et al. ACE 2005 multilingual training corpus［DS/OL］. （2016-02-15）［2022-02-12］..
10	ZELENKO D， AONE C， RICHARDELLA A. Kernel methods for relation extraction［C］// Proceedings of the 2002 Conference on Empirical Methods in Natural Language Processing. Stroudsburg， PA： ACL， 2002： 71-78. 10.3115/1118693.1118703
11	SUI D B， CHEN Y B， LIU K， et al. Joint entity and relation extraction with set prediction networks［EB/OL］. （2020-11-10）［2022-02-11］.. 10.1109/tnnls.2023.3264735
12	METKE-JIMENEZ A， KARIMI S. Concept extraction to identify adverse drug reactions in medical forums： a comparison of algorithms［EB/OL］. （2015-04-27）［2022-01-14］.. 10.1145/2632188.2632200
13	FISHER J， VLACHOS A. Merge and label： a novel neural network architecture for nested NER［C］// Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. Stroudsburg， PA： ACL， 2019： 5840-5850. 10.18653/v1/p19-1585
14	JU M Z， 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： Human Language Technologies， Volume 1 （Long Papers）. Stroudsburg， PA： ACL， 2018： 1446-1459. 10.18653/v1/n18-1131
15	SHIBUYA T， HOVY E. Nested named entity recognition via second-best sequence learning and decoding［J］. Transactions of the Association for Computational Linguistics， 2020， 8： 605-620. 10.1162/tacl_a_00334
16	WANG Y R， SHINDO H， MATSUMOTO Y， et al. Nested named entity recognition via explicitly excluding the influence of the best path［C］// Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing （Volume 1： Long Papers）. Stroudsburg， PA： ACL， 2021： 3547-3557. 10.18653/v1/2021.acl-long.275
17	SOHRAB M G， MIWA M. Deep exhaustive model for nested named entity recognition［C］// Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. Stroudsburg， PA： ACL， 2018： 2843-2849. 10.18653/v1/d18-1309
18	LI X Y， FENG J R， MENG Y X， et al. A unified MRC framework for named entity recognition［C］// Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Stroudsburg， PA： ACL， 2020： 5849-5859. 10.18653/v1/2020.acl-main.519
19	LI X， YANG J N， LIU H， et al. HTLinker： a head-to-tail linker for nested named entity recognition［J］. Symmetry， 2021， 13（9）： No.1596. 10.3390/sym13091596
20	STRAKOVÁ J， STRAKA M， HAJIC J. Neural architectures for nested NER through linearization［C］// Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. Stroudsburg， PA： ACL， 2019： 5326-5331. 10.18653/v1/p19-1527
21	TAN Z Q， SHEN Y L， ZHANG S， et al. A sequence-to-set network for nested named entity recognition［C］// Proceedings of the 30th International Joint Conference on Artificial Intelligence. California： ijcai.org， 2021： 3936-3942. 10.24963/ijcai.2021/542
22	KATIYAR A， CARDIE C. Nested named entity recognition revisited［C］// Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics： Human Language Technologies， Volume 1 （Long Papers）. Stroudsburg， PA： ACL， 2018： 861-871. 10.18653/v1/n18-1079
23	GUPTA P， YASEEN U， SCHÜTZE H. Linguistically informed relation extraction and neural architectures for nested named entity recognition in BioNLP-OST 2019［C］// Proceedings of the 5th Workshop on BioNLP Open Shared Tasks. Stroudsburg， PA： ACL， 2019： 132-142. 10.18653/v1/d19-5720
24	ZHANG H Y， ZHANG G Q， MA Y. Syntax-informed self-attention network for span-based joint entity and relation extraction［J］. Applied Sciences， 2021， 11（4）： No.1480. 10.3390/app11041480
25	DEVLIN J， CHANG M W， LEE K， et al. BERT： pre-training of deep bidirectional transformers for language understanding［C］// Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics： Human Language Technologies， Volume 1 （Long and Short Papers）. Stroudsburg， PA： ACL， 2019： 4171-4186. 10.18653/v1/n18-2
26	YU B W， ZHANG Z Y， SHU X B， et al. Joint extraction of entities and relations based on a novel decomposition strategy［C］// Proceedings of the 24th European Conference on Artificial Intelligence. Amsterdam： IOS Press， 2020： 2006-2013.
27	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
28	YAN H， GUI T， DAI J Q， et al. A unified generative framework for various NER subtasks［C］// Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing （Volume 1： Long Papers）. Stroudsburg， PA： ACL， 2021： 5808-5822. 10.18653/v1/2021.acl-long.451
29	LOSHCHILOV I， HUTTER F. Decoupled weight decay regularization［EB/OL］. （2019-01-04）［2022-04-09］..

类目	实例
句子	王某是｛［（某校）某协会］会长｝
嵌套实体内三元组	｛某校学生会，学校，某校｝
嵌套实体间三元组	｛王某，职位，某校学生会会长｝
	｛王某，部门，某校学生会｝
	｛王某，国家，某校｝

类目	实例
句子	王某是｛［（某校）某协会］会长｝
嵌套实体内三元组	｛某校学生会，学校，某校｝
嵌套实体间三元组	｛王某，职位，某校学生会会长｝
	｛王某，部门，某校学生会｝
	｛王某，国家，某校｝

数据集	训练集实体数	验证集实体数	测试集实体数	嵌套实体比率/%
ACE2005	7 194	969	1 047	36.4
WebNLG	5 019	500	703	6.8
SciERC	1 861	275	551	9.5
NYT	56 196	5 000	5 000	1.0

数据集	训练集实体数	验证集实体数	测试集实体数	嵌套实体比率/%
ACE2005	7 194	969	1 047	36.4
WebNLG	5 019	500	703	6.8
SciERC	1 861	275	551	9.5
NYT	56 196	5 000	5 000	1.0

数据集	模型	Prec	Rec	F1
NYT	TPLinker（LSTM）^［2］	86.00	82.00	84.00
	TPLinker（BERT）^［2］	91.40	92.60	92.00
	SPN^［11］	92.50	92.20	92.30
	EF2LTF	93.00	93.10	93.10
WebNLG	TPLinker（LSTM）^［2］	91.90	81.60	86.40
	TPLinker（BERT）^［2］	88.90	84.50	86.70
	SPN^［11］	85.20	82.40	83.80
	EF2LTF	90.30	87.20	88.80
SciERC	SciIE^［8］	47.60	33.50	39.30
	DyGIE^［3］	—	—	41.60
	SpERT（BERT）^［5］	49.79	43.53	46.44
	DyGIE++^［4］	—	—	48.40
	SpERT（SciBERT）^［5］	53.40	48.54	50.84
	EF2LTF	57.17	46.61	51.35
ACE2005	SPN^［11］	48.39	39.28	43.36
	TPLinker（BERT）^［2］	65.78	32.54	43.54
	DyGIE++^［4］	58.46	39.72	47.30
	SpERT（BERT）^［5］	51.51	52.97	52.23
	EF2LTF	59.61	50.81	54.86

Forest-based entity-relation joint extraction model

基于森林的实体关系联合抽取模型

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 7

References 29

Related Articles 15

Recommended Articles

Metrics

[1]	ZHANG Qing, YANG Fan, FANG Yuhan. Chinese Spelling Correction Algorithm Based on Multi-Modal Information Fusion [J]. Journal of Computer Applications, 0, (): 0-0.
[2]	Yingjie GAO, Min LIN, Siriguleng, Bin LI, Shujun ZHANG. Prompt learning method for ancient text sentence segmentation and punctuation based on span-extracted prototypical network [J]. Journal of Computer Applications, 2024, 44(12): 3815-3822.
[3]	. Fault diagnosis method for train control on-board interface equipment of CTCS-3 based on temporal knowledge graph completion [J]. Journal of Computer Applications, 0, (): 0-0.
[4]	. Metaphor detection technique for improving representation in linguistic rules [J]. Journal of Computer Applications, 0, (): 0-0.
[5]	. Optimization method for sequence labeling combined with entity boundary offset [J]. Journal of Computer Applications, 0, (): 0-0.
[6]	. Chinese spelling correction model ReLM enhanced with deep semantic features [J]. Journal of Computer Applications, 0, (): 0-0.
[7]	. Nested named entity recognition combined with boundary generation by multi-objective learning [J]. Journal of Computer Applications, 0, (): 0-0.
[8]	. Survey of sequential pattern mining [J]. Journal of Computer Applications, 0, (): 0-0.
[9]	. Deep semi-supervised text clustering with intentional regularization [J]. Journal of Computer Applications, 0, (): 0-0.
[10]	. Combining preprocessing methods and adversarial learning for fair link prediction [J]. Journal of Computer Applications, 0, (): 0-0.
[11]	. Dependency type and distance enhanced aspect based sentiment analysis model [J]. Journal of Computer Applications, 0, (): 0-0.
[12]	. Nested entity recognition model for wind power equipment based on differential boundary enhancement [J]. Journal of Computer Applications, 0, (): 0-0.
[13]	. Visually guided word segmentation and part of speech [J]. Journal of Computer Applications, 0, (): 0-0.
[14]	. Aspect-based sentiment analysis method with code generation [J]. Journal of Computer Applications, 0, (): 0-0.
[15]	Yushan JIANG, Yangsen ZHANG. Large language model-driven stance-aware fact-checking [J]. Journal of Computer Applications, 2024, 44(10): 3067-3073.

模型	Prec	Rec	F1
EF2LTF	59.61	50.81	54.86
EF2LTF（-ETI）	59.51	49.99	54.29
EF2LTF（-ETI-LTF）	46.20	42.79	44.43
EF2LTF（-ETI-LTF-EF）	48.39	39.28	43.36

模型	Prec	Rec	F1
EF2LTF	59.61	50.81	54.86
EF2LTF（-ETI）	59.51	49.99	54.29
EF2LTF（-ETI-LTF）	46.20	42.79	44.43
EF2LTF（-ETI-LTF-EF）	48.39	39.28	43.36