基于图注意力神经网络的实体消歧方法

doi:10.6040/j.issn.1671-9352.1.2022.4484

《山东大学学报(理学版)》 ›› 2024, Vol. 59 ›› Issue (3): 71-80, 94.doi: 10.6040/j.issn.1671-9352.1.2022.4484

基于图注意力神经网络的实体消歧方法

牛泽群¹(),李晓戈^1,^2,^3,*(),强成宇¹,韩伟¹,姚怡¹,刘洋³

1. 西安邮电大学计算机学院, 陕西西安 710121
2. 西安邮电大学陕西省网络数据分析与智能处理重点实验室, 陕西西安 710121
3. 西安邮电大学西安市知识发现与应用工程技术中心, 陕西西安 710121

收稿日期:2022-09-29 出版日期:2024-03-20 发布日期:2024-03-06
通讯作者: 李晓戈 E-mail:1356903944@qq.com;lixg@xupt.edu.cn
作者简介:牛泽群(1996—)，男，硕士研究生，研究方向为自然语言处理. E-mail: 1356903944@qq.com
基金资助:
国家重点研发计划资助项目(2018YFB1402905);陕西省重点研发计划资助项目(2020GY-227);陕西省重点研发计划资助项目(2020ZDLGY09-05);陕西省技术创新引导专项基金(2022PT-49)

Entity disambiguation method based on graph attention networks

Zequn NIU¹(),Xiaoge LI^1,^2,^3,*(),Chengyu QIANG¹,Wei HAN¹,Yi YAO¹,Yang LIU³

1. School of Computer Science and Technology, Xi'an University of Posts and Telecommunications, Xi'an 710121, Shaanxi, China
2. Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing, Xi'an University of Posts and Telecommunications, Xi'an 710121, Shaanxi, China
3. Xi'an Knowledge Discovery and Application Engineering Technology Center, Xi'an University of Posts and Telecommunications, Xi'an 710121, Shaanxi, China

Received:2022-09-29 Online:2024-03-20 Published:2024-03-06
Contact: Xiaoge LI E-mail:1356903944@qq.com;lixg@xupt.edu.cn

摘要/Abstract

摘要：

针对链接对象为存在半结构化数据的知识库, 提出了一种基于图注意力神经网络的短文本实体指称消歧方法。通过信息抽取与融入关键词, 将含有半结构化数据的知识库构建为全局知识图谱; 同时基于Bert预训练模型对短文本中的实体指称项进行嵌入融合; 使用图注意力神经网络对全局知识图谱中候选实体节点进行加权聚合表征, 并计算实体指称项与各候选实体之间的相似度得分, 实现实体消歧。在CCKS2019数据集上的实验结果表明, 基于图注意力神网络的实体消歧模型有效提高了实体消歧效果。

关键词: 实体消歧, 知识图谱, 关键词提取, 图注意力神经网络, 自然语言处理

Abstract:

We propose an entity disambiguation method based on graph attention networks for semi-structured knowledge base data. First, a global knowledge graph is constructed from the semi-structured knowledge base, and the entity reference items are embedded by Bert pre-trained model meanwhile. Next, graph attention networks which leverages masked self-attention layers is applyed on candidate entity nodes of global knowledge graph to fetch a vector of node level. Furtherly, we com pute similarity scores rank between the entity reference items and the candidate entity to complete the task of entity disambiguation. The experimental results on CCKS2019 dataset achieve state-of-the-art.

Key words: entity disambiguation, knowledge graph, keyword extraction, graph attention networks, natural language processing

中图分类号:

TP391

牛泽群,李晓戈,强成宇,韩伟,姚怡,刘洋. 基于图注意力神经网络的实体消歧方法[J]. 《山东大学学报(理学版)》, 2024, 59(3): 71-80, 94.

Zequn NIU,Xiaoge LI,Chengyu QIANG,Wei HAN,Yi YAO,Yang LIU. Entity disambiguation method based on graph attention networks[J]. JOURNAL OF SHANDONG UNIVERSITY(NATURAL SCIENCE), 2024, 59(3): 71-80, 94.

图/表 16

图1

图2

图3

图4

图5

图6

表1

表2

图7

表3

表4

图8

图9

图10

表5

表6

参考文献 32

1	李天然, 刘明童, 张玉洁, 等. 基于深度学习的实体链接研究综述[J]. 北京大学学报(自然科学版), 2021, 57 (1): 91- 98.
	LI Ziran , LIU Mingtong , ZHANG Yujie , et al. Review of entity linking research based on deep learning[J]. Journal of Peking University(Natural Science Edition), 2021, 57 (1): 91- 98.
2	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.
	LIU Qiao , LI Yang , DUAN Hong , et al. Overview of knowledge graph construction technology[J]. Computer Research and Development, 2016, 53 (3): 582- 600.
3	段宗涛, 李菲, 陈柘. 实体消歧综述[J]. 控制与决策, 2021, 36 (5): 1025- 1039.
	DUAN Zongtao , LI Fei , CHEN Zhe . Overview of entity disambiguation[J]. Control and Decision, 2021, 36 (5): 1025- 1039.
4	BOIŃSKI T , SZYMAŃSKI J , DUDEK B , et al. NLP questions answering using DBpedia and YAGO[J]. Vietnam Journal of Computer Science, 2020, (3): 1- 16.
5	SINGH K , LYTRA I , RADHAKRISHNA S A , et al. No one is perfect: analysing the performance of question answering components over the DBpedia knowledge graph[J]. Journal of Web Semantics, 2020, 65 (1): 100594.
6	HUANG Zhipeng , BOGDAN C , REYNOLD C , et al. Entity-based query recommendation for long-tail queries[J]. ACM Transactions on Knowledge Discovery from Data, 2018, 12 (6): 1- 24.
7	张丹阳, 李楠, 陈翀. 实体链接技术研究述评[J]. 情报工程, 2020, 6 (6): 45- 55.
	ZHANG Danyang , LI Nan , CHEN Chong . Review of research on entity link technology[J]. Information Engineering, 2020, 6 (6): 45- 55.
8	HUANG D , WANG J . An approach on Chinese microblog entity linking combining baidu encyclopaedia and word2vec[J]. Procedia Computer Science, 2017, 111, 37- 45. doi: 10.1016/j.procs.2017.06.007
9	GUO Zhaochen , BARBOSA Denilson . Robust named entity disambiguation with random walks[J]. Semantic Web, 2017, 9 (11): 1- 21.
10	武川, 陆伟. 基于上下文特征的短文本实体链接研究[J]. 情报科学, 2016, (2): 144- 147.
	WU Chuan , LU Wei . Research on short text entity linking based on context features[J]. Intelligence Science, 2016, (2): 144- 147.
11	谭咏梅, 王睿, 李茂林. 基于上下文信息和排序学习的实体链接方法[J]. 北京邮电大学学报, 2015, (5): 33- 36.
	TAN Yongmei , WANG Rui , LI Maolin . Entity linking method based on context information and ranking learning[J]. Journal of Beijing University of Posts and Telecommunications, 2015, (5): 33- 36.
12	昝红英, 吴泳钢, 贾玉祥, 等. 基于多源知识的中文微博命名实体链接[J]. 山东大学学报(理学版), 2015, (7): 9- 16.
	ZAN Hongying , WU Yonggang , JIA Yuxiang , et al. Chinese Weibo named entity link based on multi-source knowledge[J]. Journal of Shandong University(Natural Science), 2015, (7): 9- 16.
13	周鹏程, 武川, 陆伟. 基于多知识库的短文本实体链接方法研究: 以Wikipedia和Freebase为例[J]. 现代图书情报技术, 2016, (6): 1- 11.
	ZHOU Pengcheng , WU Chuan , LU Wei . Research on short text entity linking method based on multiple knowledge bases: taking Wikipedia and Freebase as examples[J]. Modern Library and Information Technology, 2016, (6): 1- 11.
14	SUN Chenchen , SHEN Derong , KOU Yue , et al. Topological features based entity disambiguation[J]. Journal of Computer Science and Technology, 2016, 31 (5): 1053- 1068.
15	FRANCIS-LANDAU M, DURRETT G, KLEIN D. Capturing semantic similarity for entity linking with convolutional neural networks[J/OL]. arXiv, 2016. https://arxiv.org/pdf/1604.00734.pdf.
16	HUANG H , HECK L , JI H . Leveraging deep neural networks and knowledge graphs for entity disambiguation[J]. CoRR, 2015,
17	张涛, 刘康, 赵军. 一种基于图模型的维基概念相似度计算方法及其在实体链接系统中的应用[J]. 中文信息学报, 2015, 29 (2): 58- 67.
	ZHANG Tao , LIU Kang , ZHAO Jun . A graph model based Wiki concept similarity calculation method and its application in entity link systems[J]. Chinese Journal of Information Technology, 2015, 29 (2): 58- 67.
18	周金, 朱永华, 张铁男, 等. 基于图的联合特征实体链接方法[J]. 上海大学学报(自然科学版), 2020, 26 (5): 747- 755.
	ZHOU Jin , ZHU Yonghua , ZHANG Tienan , et al. Graph based joint feature entity linking method[J]. Journal of Shanghai University(Natural Science), 2020, 26 (5): 747- 755.
19	郭宇航, 秦兵, 刘挺, 等. 实体链指技术研究进展[J]. 智能计算机与应用, 2014, 4 (5): 9- 13.
	GUO Yuhang , QIN Bing , LIU Ting , et al. Research progress in physical chain finger technology[J]. Intelligent Computers and Applications, 2014, 4 (5): 9- 13.
20	MULANG' I O, SINGH K, PRABHU C, et al. Evaluating the impact of knowledge graph context on entity disambiguation models[C]//Proceedings of the 29th ACM International Conference on Information & Knowledge Management. New York: ACM, 2020: 2157-2160.
21	CETOLI A, BRAGAGLIA S, O' HARNEY A D, et al. A neural approach to entity linking on wikidata[C]//European Conference on Information Retrieval. Berlin: Springer, 2019: 78-86.
22	祁志卫, 王笳辉, 岳昆, 等. 图嵌入方法与应用: 研究综述[J]. 电子学报, 2020, 48 (4): 808- 818.
	QI Zhiwei , WANG Jiahui , YUE Kun , et al. Graph embedding methods and applications: research review[J]. Journal of Electronics, 2020, 48 (4): 808- 818.
23	WANG D, CUI P, ZHU W. Structural deep network embedding[C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York: ACM, 2016: 1225-1234.
24	CAO S, LU W, XU Q. Deep neural networks for learning graph representations[C]//Proceedings of the AAAI Conference on Artificial Intelligence. [S. l. ]: AAAI, 2016, 30(1).
25	HAMILTON W L, YING R, LESKOVEC J. Inductive representation learning on large graphs[J/OL]. arXiv, 2017. https://arxiv.org/pdf/1706.02216.pdf.
26	KIPF T N, WELLING M. Semi-supervised classification with graph convolutional networks[J/OL]. arXiv, 2016. https://arxiv.org/abs/1609.02907.
27	VELIČKOVIC' P, CUCURULL G, CASANOVA A, et al. Graph attention networks[J]. arXiv, 2017. https://arxiv.org/abs/1710.10903.
28	张玉帅, 赵欢, 李博. 基于BERT和BiLSTM的语义槽填充[J]. 计算机科学, 2021, 48 (1): 247- 252.
	ZHANG Yushuai , ZHAO Huan , LI Bo . Semantic slot filling based on BERT and BiLSTM[J]. Computer Science, 2021, 48 (1): 247- 252.
29	DEVLIN J, CHANG M W, LEE K, et al. Bert: pre-training of deep bidirectional transformers for language understanding[J/OL]. arXiv, 2018. https://arxiv.org/abs/1810.04805v2.
30	VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[J/OL]. arXiv, 2017. https://arxiv.org/abs/1706.03762v3.
31	金燕, 黄杰. 基于信息熵与词长信息改进的TFIDF算法[J]. 浙江工业大学学报, 2021, 49 (2): 203- 209.
	JIN Yan , HUANG Jie . Improved TFIDF algorithm based on information entropy and word length information[J]. Journal of Zhejiang University of Technology, 2021, 49 (2): 203- 209.
32	张晟旗, 王元龙, 李茹, 等. 基于局部注意力机制的中文短文本实体链接[J]. 计算机工程, 2021, 47 (11): 77- 83.
	ZHANG Shengqi , WANG Yuanlong , LI Ru , et al. Chinese short text entity link based on local attention mechanism[J]. Computer Engineering, 2021, 47 (11): 77- 83.

多维度评价

Viewed

Full text

Abstract

Cited

Shared

Discussed

实体类型	实体举例
候选实体(subject)	想你的夜
别称	Miss You Nights
属性值	女人如歌第四期
摘要文本	《想你的夜》是史丹丹的音乐作品, 收录在《女人如歌第四期》专辑中。

关系类型	三元组	三元组举例
别名	〈候选实体, 别名, 别称〉	〈想你的夜, 别名, Miss You Nights〉
属性	〈候选实体, 属性, 属性值〉	〈想你的夜, 所属专辑, 女人如歌第四期〉
摘要	〈候选实体, 摘要, 摘要文本〉	〈想你的夜, 摘要, 摘要文本〉

实体类型	实体举例
关键词	情歌

关系类型	三元组	三元组举例
Key word	〈候选实体, Key word, 关键词〉	〈想你的夜, Key word, 情歌〉

模型	A/%	P	R	F₁
BERT	77.7	0.76	0.78	0.77
BERT+GAT	72.2	0.71	0.72	0.71
BERT+Tf-Idf+GAT	81.3	0.83	0.82	0.82

基于图注意力神经网络的实体消歧方法

Entity disambiguation method based on graph attention networks

RichHTML

PDF (PC)

摘要/Abstract

引用本文

使用本文

图/表 16

参考文献 32

相关文章 4

多维度评价

本文评价

推荐阅读 10

[1]	那宇嘉,谢珺,杨海洋,续欣莹. 融合上下文的知识图谱补全方法[J]. 《山东大学学报(理学版)》, 2023, 58(9): 71-80.
[2]	马飞翔,廖祥文,於志勇,吴运兵,陈国龙. 基于知识图谱的文本观点检索方法[J]. 山东大学学报（理学版）, 2016, 51(11): 33-40.
[3]	谭红叶, 赵健, 陈千. 基于不一致的汉语句法树库潜在错误查找[J]. 山东大学学报（理学版）, 2015, 50(01): 26-30.
[4]	陈珂锐,潘君. 基于扩展特征向量空间模型的多源数据融合[J]. J4, 2013, 48(11): 87-92.