Relation extraction model based on multi-scale hybrid attention convolutional neural networks

doi:10.11772/j.issn.1001-9081.2023081183

Journal of Computer Applications ›› 2024, Vol. 44 ›› Issue (7): 2011-2017.DOI: 10.11772/j.issn.1001-9081.2023081183

• Artificial intelligence • Previous Articles Next Articles

Relation extraction model based on multi-scale hybrid attention convolutional neural networks

Yuan TANG¹^,²^,³, Yanping CHEN¹^,²^,³(), Ying HU¹^,²^,³, Ruizhang HUANG¹^,²^,³, Yongbin QIN¹^,²^,³

^1.Text Computing and Cognitive Intelligence Engineering Research Center of Ministry of Education，Guizhou University，Guiyang Guizhou 550025，China
^2.State Key Laboratory of Public Big Data （Guizhou University），Guiyang Guizhou 550025，China
^3.College of Computer Science and Technology，Guizhou University，Guiyang Guizhou 550025，China

Received:2023-09-03 Revised:2023-10-13 Accepted:2023-10-17 Online:2024-07-18 Published:2024-07-10
Contact: Yanping CHEN
About author:TANG Yuan， born in 1999， M. S. candidate. Her research interests include natural language processing， information extraction.
HU Ying， born in 1996， Ph. D. candidate. His research interests include natural language processing.
HUANG Ruizhang， born in 1979， Ph. D.， professor. Her research interests include big data and data mining， information extraction.
QIN Yongbin， born in 1980， Ph. D.， professor. His research interests include big data management and application， multi-source data fusion and application.
First author contact:CHEN Yanping， born in 1980， Ph. D.， professor. His research interests include artificial intelligence， natural language processing.
Supported by:
National Natural Science Foundation of China(62166007);Key Technology Research and Development Program of Guizhou Province(［2022］277)

基于多尺度混合注意力卷积神经网络的关系抽取模型

唐媛¹^,²^,³, 陈艳平¹^,²^,³(), 扈应¹^,²^,³, 黄瑞章¹^,²^,³, 秦永彬¹^,²^,³

^1.贵州大学文本计算与认知智能教育部工程研究中心, 贵阳 550025
^2.公共大数据国家重点实验室(贵州大学), 贵阳 550025
^3.贵州大学计算机科学与技术学院, 贵阳 550025

通讯作者: 陈艳平
作者简介:唐媛（1999—），女，四川遂宁人，硕士研究生，主要研究方向：自然语言处理、信息抽取；
扈应（1996—），男，重庆人，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：大数据与数据挖掘、信息提取；
秦永彬（1980—），男，山东烟台人，教授，博士，CCF高级会员，主要研究方向：大数据管理与应用、多源数据融合与应用。
第一联系人：陈艳平（1980—），男，贵州长顺人，教授，博士，CCF会员，主要研究方向：人工智能、自然语言处理；
基金资助:
国家自然科学基金资助项目(62166007);贵州省科技支撑计划项目(［2022］277)

Abstract

Abstract:

To address the issue of insufficient extraction of semantic feature information with different scales and the lack of focus on crucial information when obtaining sentence semantic information by Convolutional Neural Network （CNN）-based relation extraction， a model for relation extraction based on a multi-scale hybrid attention CNN was proposed. Firstly， relation extraction was modeled as label prediction with two-dimensional representation. Secondly， by extracting and fusing multi-scale feature information， finer-grained multi-scale spatial information was obtained. Thirdly， through the combination of attention and convolution， the feature maps were refined adaptively to make the model concentrate on important contextual information. Finally， two predictors were used jointly to predict the relation labels between entity pairs. Experimental results demonstrate that the multi-scale hybrid convolutional attention model can capture multi-scale semantic feature information，And the key information in channels and spatial locations was captured by the channel attention and spatial attention by assigning appropriate weights， thereby improving the performance of relation extraction. The proposed model achieves F1 scores of 90.32% on SemEval （SemEval-2010 task 8） dataset， 70.74% on TACRED （TAC Relation Extraction Dataset）， 85.71% on Re-TACRED （Revised-TACRED）， and 89.66% on SciERC （Entities， Relations， and Coreference for Scientific knowledge graph construction）.

Key words: relation extraction, two-dimensional representation, channel attention, spatial attention, multi-scale semantic feature

摘要：

针对基于卷积神经网络（CNN）的关系抽取获取句子语义信息时缺少不同尺度语义特征信息的获取以及对关键信息的关注的问题，提出基于多尺度混合注意力CNN的关系抽取模型。首先，将关系抽取建模为二维化表示的标签预测；其次，通过多尺度的特征信息提取与融合，获得更细粒度的多尺度空间信息；然后，通过注意力与卷积的结合自适应地细化特征图，使模型关注重要的上下文信息；最后，使用两个预测器共同预测实体对之间的关系标签。实验结果表明，多尺度混合卷积注意力模型能够获取多尺度语义特征信息，而通道注意力和空间注意力通过权重捕捉通道和空间的关键信息，以此来提升关系抽取的性能。所提模型在数据集SemEval （SemEval-2010 task 8）、TACRED （TAC Relation Extraction Dataset）、Re-TACRED （Revised-TACRED）和SciERC （Entities， Relations， and Coreference for Scientific knowledge graph construction）上的F1值分别达到90.32%、70.74%、85.71%和89.66%。

关键词: 关系抽取, 二维化表示, 通道注意力, 空间注意力, 多尺度语义特征

CLC Number:

TP391

Yuan TANG, Yanping CHEN, Ying HU, Ruizhang HUANG, Yongbin QIN. Relation extraction model based on multi-scale hybrid attention convolutional neural networks[J]. Journal of Computer Applications, 2024, 44(7): 2011-2017.

唐媛, 陈艳平, 扈应, 黄瑞章, 秦永彬. 基于多尺度混合注意力卷积神经网络的关系抽取模型[J]. 《计算机应用》唯一官方网站, 2024, 44(7): 2011-2017.

Figures/Tables 10

References 29

1	XU K， REDDY S， FENG Y， et al. Question answering on freebase via relation extraction and textual evidence ［C］// Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics （Volume 1： Long Papers）. Stroudsburg： ACL， 2016： 2326-2336.
2	DISTIAWAN B， WEIKUM G， QI J， et al. Neural relation extraction for knowledge base enrichment ［C］// Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. Stroudsburg： ACL， 2019： 229-240.
3	SUN K， ZHANG R， MENSAH S， et al. Aspect-level sentiment analysis via convolution over dependency tree ［C］// Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing. Stroudsburg： ACL， 2019： 5679-5688.
4	MA Y， HIRAOKA T， OKAZAKI N. Joint entity and relation extraction based on table labeling using convolutional neural networks ［C］// Proceedings of the 6th Workshop on Structured Prediction for NLP. Stroudsburg： ACL， 2022： 11-21.
5	ZENG D， LIU K， CHEN Y， et al. Distant supervision for relation extraction via piecewise convolutional neural networks ［C］// Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing. Stroudsburg： ACL， 2015： 1753-1762.
6	李子茂，张玥，尹帆，等.基于自注意力与分段卷积神经网络的实体关系抽取［J］.中南民族大学学报（自然科学版）， 2022， 41（3）： 326-332.
	LI Z M， ZHANG Y， YIN F， et al. Entity relation extraction based on self-attention and piecewise convolutional neural network ［J］. Journal of South-Central Minzu University（Natural Science Edition）， 2022， 41（3）： 326-332.
7	VASWANI A， SHAZEER N， PARMAR N， et al. Attention is all you need ［C］// Proceedings of the 31 st International Conference on Neural Information Processing Systems. Red Hook， NY： Curran Associates Inc.， 2017： 6000-6010.
8	MNIH V， HEESS N， GRAVES A. Recurrent models of visual attention ［C］// Proceedings of the 27th International Conference on Neural Information Processing Systems： Volume 2. Cambridge： MIT Press， 2014： 2204-2212.
9	RINK B， HARABAGIU S. UTD： classifying semantic relations by combining lexical and semantic resources ［C］// Proceedings of the 5th International Workshop on Semantic Evaluation. Stroudsburg： ACL， 2010： 256-259.
10	YANG Y， TONG Y， MA S， et al. A position encoding convolutional neural network based on dependency tree for relation classification ［C］// Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing. Stroudsburg： ACL 2016： 65-74.
11	QUAN C， HUA L， SUN X， et al. Multichannel convolutional neural network for biological relation extraction ［J］. BioMed Research International， 2016， 2016： No.1850404.
12	CHEN Y， WANG K， YANG W， et al. A multi-channel deep neural network for relation extraction ［J］. IEEE Access， 2020， 8： 13195-13203.
13	LEE J， SEO S， CHOI Y S. Semantic relation classification via bidirectional LSTM networks with entity-aware attention using latent entity typing ［J］. Symmetry， 2019， 11（6）： No.785.
14	闫雄，段跃兴，张泽华.采用自注意力机制CNN融合的实体关系抽取［J］.计算机工程与科学， 2020， 42（11）： 2059-2066.
	YAN X， DUAN Y X， ZHANG Z H. Entity relationship extraction fusing self-attention mechanism and CNN ［J］. Computer Engineering and Science， 2020， 42（11）： 2059-2066.
15	SHEN Y， HUANG X. Attention-based convolutional neural network for semantic relation extraction ［C］// Proceedings of the 26th International Conference on Computational Linguistics： Technical Papers. ［S.l.］： The COLING 2016 Organizing Committee， 2016： 2526-2536.
16	TIAN Y， CHEN G， SONG Y， et al. Dependency-driven relation extraction with attentive graph convolutional networks ［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： ACL， 2021： 4458-4471.
17	隗昊，唐焕玲，周爱，等.基于双路分段注意力神经张量网络的临床文本关系抽取［J］.电子学报， 2023， 51（3）： 658-665.
	WEI H， TANG H L， ZHOU A， et al. Clinical relation via dual piecewise attention neural tensor network ［J］. Acta Electronica Sinica， 2023， 51（3）： 658-665.
18	ZHOU L， WANG T， QU H， et al. A weighted GCN with logical adjacency matrix for relation extraction ［C］// Proceedings of the 24th European Conference on Artificial Intelligence. Amsterdam： IOS Press， 2020： 2314-2321.
19	HENDRICKX I， KIM S N， KOZAREVA Z， et al. SemEval-2010 Task 8： multi-way classification of semantic relations between pairs of nominals［C］// Proceedings of the 5th International Workshop on Semantic Evaluation. Stroudsburg： ACL， 2010：28-33-38.
20	ZHANG Y， ZHONG V， CHEN D， et al. Position-aware attention and supervised data improve slot filling ［C］// Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing. Stroudsburg： ACL， 2017： 35-45.
21	STOICA G， PLATANIOS E A， PÓCZOS B. Re-tacred： addressing shortcomings of the tacred dataset ［C］// Proceedings of the 35th AAAI Conference on Artificial Intelligence. Menlo Park， CA： AAAI Press， 2021： 13843-13850.
22	LUAN Y， HE L， 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： ACL， 2018： 3219-3232.
23	ZHANG Y， QI P， MANNING C D. Graph convolution over pruned dependency trees improves relation extraction ［C］// Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. Stroudsburg： ACL， 2018： 2205-2215.
24	LI B， YU D， YE W， et al. Sequence generation with label augmentation for relation extraction ［C］// Proceedings of the 37th AAAI Conference on Artificial Intelligence. Palo Alto， CA： AAAI Press， 2023： 13043-13050.
25	WU S， HE Y. Enriching pre-trained language model with entity information for relation classification ［C］// Proceedings of the 28th ACM International Conference on Information and Knowledge Management. New York： ACM， 2019： 2361-2364.
26	TIAN Y， SONG Y， XIA F. Improving relation extraction through syntax-induced pre-training with dependency masking ［C］// Findings of the Association for Computational Linguistics： ACL 2022. Stroudsburg： ACL， 2022： 1875-1886.
27	JOSHI M， CHEN D， LIU Y， et al. SpanBERT： improving pre-training by representing and predicting spans ［J］. Transactions of the Association for Computational Linguistics， 2020， 8： 64-77.
28	HUGUET CABOT P L， NAVIGLI R. REBEL： relation extraction by end-to-end language generation ［C］// Findings of the Association for Computational Linguistics. Stroudsburg： ACL， 2021： 2370-2381.
29	LI J， FEI H， LIU J， et al. Unified named entity recognition as word-word relation classification ［C］// Proceedings of the 36th AAAI Conference on Artificial Intelligence. Palo Alto， CA： AAAI Press， 2022： 10965-10973.

数据集	样本数			关系数
数据集	训练集	测试集	验证集	关系数
SemEval	8 000	2 717	—	19
TACRED	68 124	22 631	25 509	42
Re-TACRED	58 465	13 418	19 584	40
SciERC	3 219	974	455	7

数据集	样本数			关系数
数据集	训练集	测试集	验证集	关系数
SemEval	8 000	2 717	—	19
TACRED	68 124	22 631	25 509	42
Re-TACRED	58 465	13 418	19 584	40
SciERC	3 219	974	455	7

参数	设置
批次大小	16
迭代次数	20
随机失活率	0.5
学习率	1×10^-3
多尺度卷积核大小	［3，5，7，9］
词向量维度	768
特征图维度	64

参数	设置
批次大小	16
迭代次数	20
随机失活率	0.5
学习率	1×10^-3
多尺度卷积核大小	［3，5，7，9］
词向量维度	768
特征图维度	64

数据集	模型	精确率	召回率	F1值
SemEval	R-BERT^［25］	—	—	89.25
	RE-DMP^［26］	—	—	89.65
	A-GCN^［16］	—	—	89.85
	BERT-CNN（基线）	90.25	89.53	89.87
	本文模型	91.69	89.06	90.32
TACRED	WGCN^［18］	71.30	66.10	68.60
	R-BERT^［25］	—	—	69.40
	BERT-CNN（基线）	71.70	68.96	70.31
	本文模型	72.98	68.63	70.74
Re-TACRED	SpanBERT^［27］	—	—	85.30
	BERT-CNN（基线）	84.79	85.84	85.31
	本文模型	86.93	84.53	85.71
SciERC	REBEL^［28］	—	—	86.30
	BERT-CNN（基线）	87.85	90.26	89.04
	本文模型	89.80	89.52	89.66

Relation extraction model based on multi-scale hybrid attention convolutional neural networks

基于多尺度混合注意力卷积神经网络的关系抽取模型

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 10

References 29

Related Articles 15

Recommended Articles

Metrics

各模块的影响	F1值/%
-通道注意力-空间注意力	89.32
-空间注意力	90.09
-通道注意力	90.06
通道空间并行	90.10
先空间后通道	90.19
先通道后空间	90.32

[1]	Yubo ZHAO, Liping ZHANG, Sheng YAN, Min HOU, Mao GAO. Relation extraction between discipline knowledge entities based on improved piecewise convolutional neural network and knowledge distillation [J]. Journal of Computer Applications, 2024, 44(8): 2421-2429.
[2]	Tong CHEN, Fengyu YANG, Yu XIONG, Hong YAN, Fuxing QIU. Construction method of voiceprint library based on multi-scale frequency-channel attention fusion [J]. Journal of Computer Applications, 2024, 44(8): 2407-2413.
[3]	Chenqian LI, Jun LIU. Ultrasound carotid plaque segmentation method based on semi-supervision and multi-scale cascaded attention [J]. Journal of Computer Applications, 2024, 44(8): 2604-2610.
[4]	Yanjie GU, Yingjun ZHANG, Xiaoqian LIU, Wei ZHOU, Wei SUN. Traffic flow forecasting via spatial-temporal multi-graph fusion [J]. Journal of Computer Applications, 2024, 44(8): 2618-2625.
[5]	Dianhui MAO, Xuebo LI, Junling LIU, Denghui ZHANG, Wenjing YAN. Chinese entity and relation extraction model based on parallel heterogeneous graph and sequential attention mechanism [J]. Journal of Computer Applications, 2024, 44(7): 2018-2025.
[6]	Chao WEI, Yanping CHEN, Kai WANG, Yongbin QIN, Ruizhang HUANG. Relation extraction method based on mask prompt and gated memory network calibration [J]. Journal of Computer Applications, 2024, 44(6): 1713-1719.
[7]	Quan YUAN, Changping CHEN, Ze CHEN, Linfeng ZHAN. Twice attention mechanism distantly supervised relation extraction based on BERT [J]. Journal of Computer Applications, 2024, 44(4): 1080-1085.
[8]	Boyue WANG, Yingxiang LI, Jiandan ZHONG. Segmentation network for day and night ground-based cloud images based on improved Res-UNet [J]. Journal of Computer Applications, 2024, 44(4): 1310-1316.
[9]	Andi GUO, Zhen JIA, Tianrui LI. High-precision entity and relation extraction in medical domain based on pseudo-entity data augmentation [J]. Journal of Computer Applications, 2024, 44(2): 393-402.
[10]	Mengmeng CHEN, Zhiwei QIAO. Sparse reconstruction of CT images based on Uformer with fused channel attention [J]. Journal of Computer Applications, 2023, 43(9): 2948-2954.
[11]	Meijia LIANG, Xinwu LIU, Xiaopeng HU. Small target detection algorithm for train operating environment image based on improved YOLOv3 [J]. Journal of Computer Applications, 2023, 43(8): 2611-2618.
[12]	Kezheng CHEN, Xiaoran GUO, Yong ZHONG, Zhenping LI. Relation extraction method based on negative training and transfer learning [J]. Journal of Computer Applications, 2023, 43(8): 2426-2430.
[13]	Menglin HUANG, Lei DUAN, Yuanhao ZHANG, Peiyan WANG, Renhao LI. Prompt learning based unsupervised relation extraction model [J]. Journal of Computer Applications, 2023, 43(7): 2010-2016.
[14]	Jingsheng LEI, Kaijun LA, Shengying YANG, Yi WU. Joint entity and relation extraction based on contextual semantic enhancement [J]. Journal of Computer Applications, 2023, 43(5): 1438-1444.
[15]	Kai ZHANG, Zhengchu QIN, Yue LIU, Xinyi QIN. Multi-learning behavior collaborated knowledge tracing model [J]. Journal of Computer Applications, 2023, 43(5): 1422-1429.

模型	F1/%	训练时间/s	测试时间/s
BERT-CNN（基线）	89.87	110	9
本文模型	90.32	158	14

模型	F1/%	训练时间/s	测试时间/s
BERT-CNN（基线）	89.87	110	9
本文模型	90.32	158	14