跨语言情境下基于对抗的实体关系抽取模型研究

doi:10.13266/j.issn.0252-3116.2020.17.014

图书情报工作 ›› 2020, Vol. 64 ›› Issue (17): 131-144.DOI: 10.13266/j.issn.0252-3116.2020.17.014

跨语言情境下基于对抗的实体关系抽取模型研究

余传明¹, 王曼怡², 安璐³

1 中南财经政法大学信息与安全工程学院武汉 430073;
2 中南财经政法大学统计与数学学院武汉 430073;
3 武汉大学信息管理学院武汉 430072

收稿日期:2020-02-08 修回日期:2020-04-22 出版日期:2020-09-05 发布日期:2020-09-05
作者简介:余传明(ORCID:0000-0001-7099-0853),教授,E-mail:yucm@zuel.edu.cn;王曼怡(ORCID:0000-0002-0633-0073),硕士研究生;安璐(ORCID:0000-0002-5408-7135),教授,博士生导师。
基金资助:
本文系国家自然科学基金面上项目"面向跨语言观点摘要的领域知识表示与融合模型研究"（项目编号：71974202）和国家自然科学基金重大课题"国家安全大数据综合信息集成与分析方法"（项目编号：71790612）研究成果之一。

Research on the Model of Adversarial Entity Relation Extraction in Cross-Lingual Context

Yu Chuanming¹, Wang Manyi², An Lu³

1 School of Information and Safety Engineering, Zhongnan University of Economics and Law, Wuhan 430073;
2 School of Statistics and Mathematics, Zhongnan University of Economics and Law, Wuhan 430073;
3 School of Information Management, Wuhan University, Wuhan 430072

Received:2020-02-08 Revised:2020-04-22 Online:2020-09-05 Published:2020-09-05

摘要/Abstract

摘要： [目的/意义] 从实体关系抽取视角出发，将单一语言情境下的知识获取任务扩展到跨语言情境，提升低资源语言的关系抽取效果。[方法/过程] 提出一种跨语言对抗关系抽取（Cross-Lingual Adversarial Relation Extraction，CLARE）框架，将跨语言关系抽取分解为平行语料获取和对抗适应关系抽取两个子模块。通过词典扩展或自学习方法将源语言关系抽取数据集转换为目标语言数据集，在此基础上利用对抗特征适应将源语言的特征表示迁移给目标语言，再利用训练得到的目标语言关系抽取网络对目标语言进行关系分类。[结果/结论] 将本文方法应用到以ACE2005多语言数据集为基础的英语-中文、中文-英文两种跨语言关系抽取任务上，最优模型的Macro-F1值分别为0.880 1和0.842 2。实验结果表明本文提出的跨语言对抗关系抽取CLARE框架能显著提升低资源语言实体关系抽取的效果。研究结果对于改进跨语言情境下的关系抽取模型以及促进实体关系抽取研究在情报学领域的应用具有重要意义。

关键词: 跨语言信息抽取, 实体关系抽取, 深度学习, 生成对抗网络

Abstract: [Purpose/significance] From the perspective of entity relation extraction, the knowledge acquisition task in a single language context is extended to a cross-language context, and the relation extraction effect of low-resource languages is improved.[Method/process] This paper proposed a Cross-Lingual Adversarial Relation Extraction (CLARE) framework, which decomposed cross-lingual relation extraction into parallel corpus acquisition and adversarial adaptation relation extraction. Through dictionary expansion or self-learning methods, the source language relation extraction data set was converted into the target language data set. On this basis, the feature representation of the source language was transferred to the target language using adversarial feature adaptation, and then the target language relation extraction network obtained by training was used to classify the target language.[Result/conclusion] The method in this paper is applied to the English-Chinese and Chinese-English cross-lingual relation extraction task based on the ACE2005 multilingual dataset. The Macro-F1 values of the optimal models on the two tasks are 0.880 1 and 0.842 2 respectively, indicating that the proposed CLARE framework for cross-language adversarial relation extraction can significantly improve the effect of low-resource language entity relation extraction. The research results are of great significance for improving the relation extraction model in the cross-lingual context and promoting the application of entity relation extraction research in the field of information science.

Key words: cross-lingual information extraction, entity relation extraction, deep learning, generative adversarial network

中图分类号:

TP391

余传明, 王曼怡, 安璐. 跨语言情境下基于对抗的实体关系抽取模型研究[J]. 图书情报工作, 2020, 64(17): 131-144.

Yu Chuanming, Wang Manyi, An Lu. Research on the Model of Adversarial Entity Relation Extraction in Cross-Lingual Context[J]. LIS, 2020, 64(17): 131-144.

参考文献

[1] 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.
[2] 胡莺夕. 基于深度学习的多实体关系识别及自动文本摘要方法研究与实现[D].北京:北京邮电大学,2019.
[3] 郑实福,刘挺,秦兵,等.自动问答综述[J].中文信息学报,2002(6):46-52.
[4] 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.
[5] KOEHN P. A parallel corpus for statistical machine translation[C]//Proceedings of the third workshop on statistical machine translation. Stroudsburg:ACL Press, 2005:3-4.
[6] ZHAO S, GRISHMAN R. Extracting relations with integrated information using kernel methods[C]//Proceedings of the annual meeting of the Association for Computational Linguistics. Stroudsburg:ACL Press, 2005:419-426.
[7] KAMBHATLA N. Combining lexical, syntactic, and semantic features with maximum entropy models for extracting relations[C]//Proceedings of the annual meeting of the Association for Computational Linguistics. Stroudsburg:ACL Press, 2004:178-181.
[8] MILLER S, FOX H, RAMSHAW L, et al. A novel use of statistical parsing to extract information from text[C]//Proceedings of the 2000 conference of the North American chapter of the Association for Computational Linguistics. Stroudsburg:ACL Press, 2000:226-233.
[9] CULOTTA A, MCCALLUM A, BETZ J T, et al. Integrating probabilistic extraction models and data mining to discover relations and patterns in text[C]//Proceedings of language and technology conference. New York:ITC Press, 2006:296-303.
[10] BRIN S. Extracting patterns and relations from the World Wide Web[C]//Proceedings of international workshop on the Web and databases. Berlin:Springer, 1998:172-183.
[11] CRAVEN M, KUMLIEN J. Constructing biological knowledge bases by extraction information from text sources[C]//Proceedings of the seventh international conference on intelligent systems for molecular biology. Menlo Park:AAAI Press,1999:77-86.
[12] HASEGAWA T, SEKINE S, GRISHMAN R. Discovering relations among named entities from large corpora[C]//Proceedings of the annual meeting on Association for Computational Linguistics. Stroudsburg:ACL Press, 2004:415.
[13] SOCHER R, HUVAL B, MANNING C D, et al. Semantic compositionality through recursive matrix-vector spaces[C]//Proceedings of the 2012 joint conference on empirical methods in natural language processing and computational natural language learning. Stroudsburg:ACL Press, 2012:1201-1211.
[14] ZENG D J, LIU K, LAI S W, et al. Relation classification via convolutional deep neural network[C]//Proceedings of the annual meeting of the Association for Computational Linguistics. Stroudsburg:ACL Press, 2014:2335-2344.
[15] SANTOS C N D, XIANG B, ZHOU B. Classifying relations by ranking with convolutional neural networks[EB/OL].[2020-01-01]. https://arxiv.org/pdf/1504.06580.pdf.
[16] KATIYAR A, CARDIE C. Going out on a limb:joint extraction of entity mentions and relations without dependency trees[C]//Proceedings of the annual meeting of the Association for Computational Linguistics. Stroudsburg:ACL Press, 2017:917-928.
[17] ZENG D J, LIU K, CHEN Y B, et al. Distant supervision for relation extraction via piecewise convolutional neural networks[C]//Conference on empirical methods in natural language processing. Stroudsburg:ACL Press,2015:1753-1762.
[18] LIN Y K, SHEN S Q, LIU Z Y, et al. Neural relation extraction with selective attention over instances[C]//Proceedings of the annual meeting of the Association for Computational Linguistics. Stroudsburg:ACL Press, 2016:2124-2133.
[19] JI G L, LIU K, HE S Z. Distant supervision for relation extraction with sentence-level attention and entity descriptions[C]//Proceedings of national conference on artificial intelligence. Menlo Park:AAAI Press, 2017:3060-3066.
[20] REN X, WU Z Q, HE W Q, et al. CoType:joint extraction of typed entities and relations with knowledge bases[C]//Proceedings of the 26th international conference on World Wide Web. Stroudsburg:ACL Press, 2017:1015-1024.
[21] HUANG Y Y, WANG W Y. Deep residual learning for weakly-supervised relation extraction[C]//Proceedings of the 2017 conference on empirical methods in natural language processing. Stroudsburg:ACL Press, 2017:1803-1807.
[22] 蒋婷,孙建军.学术资源本体非等级关系抽取研究[J].图书情报工作,2016,60(20):112-122.
[23] 俞琰,陈磊,姜金德,等.基于依存句法分析的中文专利候选术语选取研究[J].图书情报工作,2019,63(18):109-118.
[24] 吴粤敏,丁港归,胡滨.基于注意力机制的农业金融文本关系抽取研究[J].数据分析与知识发现,2019,3(5):86-92.
[25] 朱惠,王昊,苏新宁,等.汉语领域术语非分类关系抽取方法研究[J].情报学报,2018,37(12):1193-1203.
[26] 张琴,郭红梅,张智雄.融合词嵌入表示特征的实体关系抽取方法研究[J].数据分析与知识发现,2017,1(9):8-15.
[27] 陈果,许天祥.小规模知识库指导下的细分领域实体关系发现研究[J].情报学报,2019,38(11):1200-1211.
[28] QIAN L H, HUI H T, HU Y N, et al. Bilingual active learning for relation classification via pseudo parallel corpora[C]//Proceedings of the 52nd annual meeting of the Association for Computational Linguistics. Stroudsburg:ACL Press, 2014:582-592.
[29] KIM S, JEONG M, LEE J, et al. Cross-lingual annotation projection for weakly-supervised relation extraction[J]. Transactions on Asian language information processing, 2014, 13(1):1-26.
[30] 胡亚楠,惠浩添,钱龙华,等.基于机器翻译的双语协同关系抽取[J].计算机应用研究,2015,32(3):662-665.
[31] FARUQUI M, KUMAR S. Multilingual open relation extraction using cross-lingual projection[C]//Poceedings of the 2015 conference of the North American chapter of the Association for Computational Linguistics. Stroudsburg:ACL Press, 2015:1351-1356.
[32] VERGA P, BELANGER D, STRUBELL E, et al. Multilingual relation extraction using compositional universal schema[C]//Proceedings of the 2016 conference of the North American chapter of the Association for Computational Linguistics. Stroudsburg:ACL Press, 2016:886-896.
[33] LIN Y K, LIU Z Y, SUN M S. Neural relation extraction with multi-lingual attention[C]//Proceedings of the annual meeting of the Association for Computational Linguistics. Stroudsburg:ACL Press,2017:34-43.
[34] WANG X Z, HAN X, LIN Y K, et al. Adversarial multi-lingual neural relation extraction[C]//Proceedings of the 27th international conference on computational linguistics. Stroudsburg:ACL Press, 2018:1156-1166.
[35] ZOU B W, XU Z Z, HONG Y, et al. Adversarial feature adaptation for cross-lingual relation classification[C]//Proceedings of the 27th international conference on computational linguistics. Stroudsburg:ACL Press,2018:437-448.
[36] GOODFELLOW I, POUGET-ABADIE J, MIRZA M, et al. Generative adversarial nets[C]//Proceedings of the 27th international conference on neural information processing systems. Montreal:ICONIP Press, 2014:2672-2680.
[37] CONNEAU A, LAMPLE G, RANZATO M A, et al. Word translation without parallel data[C]//Proceedings of the international conference on learning representations. Vancouver:ICLR Press, 2018.
[38] ARTETXE M, LABAKA G, and AGIRRE E. A robust self-learning method for fully unsupervised cross-lingual mappings of word embeddings[C]//Proceedings of the 56th annual meeting of the Association for Computational Linguistics. Stroudsburg:ACL,2018:789-798.
[39] IRVINE A, CALLISONBURCH C. A comprehensive analysis of bilingual lexicon induction[J]. Computational linguistics, 2017, 43(2):273-310.
[40] JOULIN A, GRAVE E, BOJANOWSKI P, et al. Bag of tricks for efficient text classification[C]//Proceedings of the 15th conference of the European chapter of the Association for Computational Linguistics. Stroudsburg:ACL Press, 2017:427-431.
[41] SHIGETO Y, SUZUKI I, HARA K, et al. Ridge regression, hubness, and zero-shot learning[C]//European conference on machine learning. Switzerland:Springer, 2015:135-151.
[42] PAPADOPOULOS S, BAKIRAS S, PAPADIAS D. Nearest neighbor search with strong location privacy[J]. Proceedings of the VLDB endowment, 2010, 3(1/2):619-629.
[43] WALKER C, STRASSEL S, MEDERO J, et al. ACE 2005 multilingual training corpus[EB/OL].[2020-02-20]. https://catalog.ldc.upenn.edu/LDC2006T06.
[44] Facebook. Word vectors for 157 languages[EB/OL] [2020-03-01]. https://fasttext.cc/docs/en/crawl-vectors.html.
[45] 余圆圆,巢文涵,何跃鹰,等.基于双语主题模型和双语词向量的跨语言知识链接[J].计算机科学,2019,46(1):238-244.
[46] 李亚超,熊德意,张民.神经机器翻译综述[J].计算机学报,2018,41(12):2734-2755.

跨语言情境下基于对抗的实体关系抽取模型研究

Research on the Model of Adversarial Entity Relation Extraction in Cross-Lingual Context

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	董美, 常志军. 一种面向中医领域科技文献的实体关系抽取方法[J]. 图书情报工作, 2022, 66(18): 105-113.
[2]	袁毅, 陶鑫琪, 李瑾萱, 刘娅娴, 汪晓芸, 景香玉. 基于招聘文本实体挖掘的人才供需分析——以人工智能领域为例[J]. 图书情报工作, 2022, 66(14): 101-118.
[3]	韩普, 顾亮. 基于混合深度学习的中文医学实体抽取研究[J]. 图书情报工作, 2022, 66(14): 119-127.
[4]	周潇, 许银彪, 史益. 基于深度学习与语义挖掘的技术创新组合识别与追踪[J]. 图书情报工作, 2022, 66(10): 33-44.
[5]	李娜, 姜恩波, 朱一真, 刘婷. 政策工具自动识别方法与实证研究[J]. 图书情报工作, 2021, 65(7): 115-122.
[6]	杜悦, 王东波, 江川, 徐润华, 李斌, 许超, 徐晨飞. 数字人文下的典籍深度学习实体自动识别模型构建及应用研究[J]. 图书情报工作, 2021, 65(3): 100-108.
[7]	桂美增, 许学国. 基于深度学习的技术机会预测研究——以新能源汽车为例[J]. 图书情报工作, 2021, 65(19): 130-141.
[8]	孔德婧, 董放, 陈子婧, 刘宇涵, 周源. 离群专利视角下的新兴技术预测——基于BERT模型和深度神经网络[J]. 图书情报工作, 2021, 65(17): 131-141.
[9]	钱力, 刘细文, 张智雄, 刘会洲. AI+智慧知识服务生态体系研究设计与应用实践——以中国科学院文献情报中心智慧服务平台建设为例[J]. 图书情报工作, 2021, 65(15): 78-90.
[10]	雷兵, 刘小, 钟镇. 基于题录信息的领域学术文献细粒度分类方法研究[J]. 图书情报工作, 2021, 65(14): 128-137.
[11]	林泽斐, 欧石燕. 融合结构与文本特征的知识图谱关系预测方法研究[J]. 图书情报工作, 2020, 64(21): 99-110.
[12]	易明, 张婷婷, 李梓. 多维特征下社会化问答社区答案排序研究[J]. 图书情报工作, 2020, 64(17): 103-113.
[13]	吕璐成, 韩涛, 周健, 赵亚娟. 基于深度学习的中文专利自动分类方法研究[J]. 图书情报工作, 2020, 64(10): 75-85.
[14]	黄水清, 王东波. 新时代人民日报分词语料库构建、性能及应用(二)——深度学习自动分词模型构建[J]. 图书情报工作, 2019, 63(23): 5-12.
[15]	邱云飞, 张伟竹. 基于网络结构和文本内容的群体画像构建方法研究[J]. 图书情报工作, 2019, 63(22): 21-30.