Chinese Short Text Entity Disambiguation Based on Multi-feature Factor Fusion

Abstract

Abstract: Most of the existing Chinese short text entity disambiguation models only consider the semantic matching features between the mention context and the description of the candidate entity in the disambiguation process， and do not consider the effective disambiguation features such as the co-occurrence features between the candidate entities in the same query text and the similarity features between the mention type of the candidate entities and entities. To solve these problems, this paper first uses the pre-training language model to obtain the semantic matching features of mention context and candidate entity description. Then, co-occurrence feature and type feature are proposed for entity embedding and mention type embedding. Finally, by fusing the above features, the entity disambiguation model based on multi feature factors is realized. The experimental results show that the co-occurrence features and type features proposed in this paper are feasible and effective in entity disambiguation, and the entity disambiguation method based on multi-feature factor fusion proposed in this paper can achieve better disambiguation effect.

Key words: co-occurrence feature, type feature, multi-feature factor, multi-head attention, Ernie

WANG Yong-di, LEI Gang. Chinese Short Text Entity Disambiguation Based on Multi-feature Factor Fusion[J]. Computer and Modernization, 2023, 0(01): 30-36.

References ［32］

［1］	BLANCO R， OTTAVIANO G， MEIJ E. Fast and space-efficient entity linking for queries［C］// Proceedings of the 8th ACM International Conference on Web Search and Data Mining. 2015:179-188.
［2］	DAS R， ZAHEER M， REDDY S， et al. Question answering on knowledge bases and text using universal schema and memory networks［C］// Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics. 2017:358-365.
［3］	DREDZE M， MCNAMEE P， RAO D， et al. Entity disambiguation for knowledge base population［C］// Proceedings of the 23rd International Conference on Computational Linguistics. 2010:277-285.
［4］	ZHAO Y， WANG Y， YANG N. Chinese short text entity linking based on semantic similarity and entity correlation［C］// 2020 IEEE 32nd International Conference on Tools with Artificial Intelligence. 2020:426-431.
［5］	FRANCIS-LANDAU M， DURRETT G， LEIN D. Capturing semantic similarity for entity linking with convolutional neural networks［J］. arXiv preprint arXiv:1604.00734， 2016.
［6］	HAN X P，SUN L. A generative entity-mention model for linking entities with knowledge base［C］// Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies. 2011: 945-954.
［7］	王瑞，李弼程，杜文倩. 基于上下文词向量和主题模型的实体消歧方法［J］. 中文信息学报， 2019， 33（11）: 46-56.
［8］	RAIMAN J， RAIMAN O. Deeptype: Multilingual entity linking by neural type system evolution［C］// Proceedings of the AAAI Conference on Artificial Intelligence. 2018:5406-5413.
［9］	YIN X Y， HUANG Y， ZHOU B， et al. Deep entity linking via eliminating semantic ambiguity with BERT［J］. IEEE Access， 2019，7:169434-169445.
［10］	DEVLIN J， CHANG M W， LEE K， et al. BERT: Pre-training of deep bidirectional transformers for language understanding［J］. arXiv preprint arXiv:1810.04805， 2018.
［11］	GANEA O E， HOFMANN T. Deep joint entity disambiguation with local neural attention［J］. arXiv preprint arXiv:1704.04920， 2017.
［12］	范鹏程，沈英汉，许洪波，等. 融合实体知识描述的实体联合消歧方法［J］. 中文信息学报， 2020，34（7）:42-49.
［13］	LIU C， LI F， SUN X， et al. Attention-based joint entity linking with entity embedding［J］. Information， 2019，10（2）: 46. DOI: 10.3390/info10020046.
［14］	HAN X P， SUN L， ZHAO J. Collective entity linking in web text: A graph-based method［C］// Proceedings of the 34th International ACM SIGIR Conference on Research and Development in Information Retrieval. 2011:765-774.
［15］	XUE M G， CAI W M， SU J S， et al. Neural collective entity linking based on recurrent random walk network learning［J］. arXiv preprint arXiv:1906.09320， 2019.
［16］	YANG X Y， GU X T， LIN S， et al. Learning dynamic context augmentation for global entity linking［J］. arXiv preprint arXiv:1909.02117， 2019.
［17］	PHAN M C， SUN A， TAY Y， et al. Pair-linking for collective entity disambiguation: Two could be better than all［J］. IEEE Transactions on Knowledge and Data Engineering， 2018，31（7）:1383-1396.
［18］	CHEN S， WANG J P， JIANG F， et al. Improving entity linking by modeling latent entity type information［J］. Proceedings of the AAAI Conference on Artificial Intelligence， 2020，34（5）:7529-7537.
［19］	冯冲，石戈，郭宇航，等. 基于词向量语义分类的微博实体链接方法［J］. 自动化学报， 2016，42（6）:915-922.
［20］	毛二松，王波，唐永旺，等. 基于词向量的中文微博实体链接方法［J］. 计算机应用与软件， 2017，34（4）:11-15.
［21］	HUANG K， CHEN X Y， WANG P. An entity linking approach for Chinese microblog［C］// 2014 International Conference on Multimedia Computing and Systems. 2014: 517-522.
［22］	FU J L， QIU J， GUO Y L， et al. Entity linking and name disambiguation using SVM in chinese micro-blogs［C］// 2015 11th International Conference on Natural Computation. 2015:468-472.
［23］	MIKOLOV T， CHEN K， CORRADO G， et al. Efficient estimation of word representations in vector space［J］. arXiv preprint arXiv:1301.3781， 2013.
［24］	ZENG W X， TANG J Y， ZHAO X. Entity linking on Chinese microblogs via deep neural network［J］. IEEE Access， 2018，6:25908-25920.
［25］	JIANG L T， ALTENBEK G， WU D， et al. Chinese short text entity disambiguation based on the dual-channel hybrid network［J］. IEEE Access， 2020，8:206164-206173.
［26］	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］. 2021，47（11）:77-83.
［27］	祝凯华，戴安南，范雪丽. 多因子融合的实体识别与链指消歧［C］// CCKS2019评测论文集. 2019.
［28］	吕荣荣，王鹏程，陈帅. 面向中文短文本的多因子融合实体链指研究［EB/OL］. （2020-10-05）［2022-01-25］. https://bj.
	bcebos.com/v1/conference/ccks2020/eval_paper/ccks2020_
	eval_paper_2_1.pdf.
［29］	SUN Y， WANG S H， LI Y K， et al. Ernie: Enhanced representation through knowledge integration［J］. arXiv preprint arXiv:1904.09223， 2019.
［30］	VASWANI A， SHAZEER N， PARMAR N， et al. Attention is all you need［C］// Proceedings of the 31st International Conference on Neural Information Processing Systems. 2017:6000-6010.
［31］	MIYATO T， DAI A M， GOODFELLOW I. Adversarial training methods for semi-supervised text classification［J］. arXiv preprint arXiv:1605.07725， 2016.
［32］	YAN Y M， LI R M， WANG S R， et al. ConSERT: A contrastive framework for self-supervised sentence representation transfer［J］. arXiv preprint arXiv:2105.11741， 2021.