JIN Cheng,CUI Rongyi,ZHAO Yahui,et al.Cross - lingual entity alignment in Chinese and Korean based on GAT and TransH[J].Journal of Yanbian University,2021,47(04):356-360.
融合GAT和TransH的中韩跨语言实体对齐方法研究
- Title:
- Cross - lingual entity alignment in Chinese and Korean based on GAT and TransH
- 文章编号:
- 1004-4353(2021)04-0356-05
- Keywords:
- Chinese - Korean cross language entity; entity alignment; knowledge graph; graph attention network
- 分类号:
- TP391
- 文献标志码:
- A
- 摘要:
- 为研究中韩双语实体自动对齐方法,提出了一种融合图注意力网络(GAT)和基于超平面平移的知识图谱嵌入模型(TransH)的跨语言实体对齐模型.使用中韩实体数据集对模型进行验证表明,该模型的Hits@1、Hits@5和Hits@10在韩文对齐中文时分别达到了49.62%、 80.89%和91.76%, 在中文对齐韩文时分别达到49.79%、 80.74%和91.67%, 且优于传统的基于知识嵌入或图嵌入的对齐方法.因此该模型可为构建中韩对齐知识图谱以及其他语言的对齐知识图谱提供参考.
- Abstract:
- To study the automatic alignment method of Chinese and Korean bilingual entities, a cross - language entity alignment model combining graph attention network(GAT)and knowledge graph embedding model based on hyperplane translation(TransH)is proposed. Validation of the model using the Chinese and Korean entity data sets shows that the Hits@1, Hits@5, and Hits@10 of the model reached 49.62%, 80.89% and 91.76% respectively, when aligning Korean to Chinese; when Chinese is aligned with Korean, it reaches 49.79%, 80.74% and 91.67% respectively. It is better than traditional alignment methods based on knowledge embedding or graph embedding. Therefore, the model can provide a reference for constructing a Chinese - Korean alignment knowledge graph and alignment knowledge graph of other languages.
参考文献/References:
[1] LI C, CAO Y, HOU L, et al.Semi - supervised entity alignment via joint knowledge embedding model and cross-graph model[C]//Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing(EMNLP - IJCNLP).Hong Kong: Association for Computational Linguistics, 2019:2723 - 2732.
[2] WANG Z, ZHANG J, FENG J, et al.Knowledge graph embedding by translating on hyperplanes[C]//Proceedings of the Twenty - Eighth AAAI Conference on Artificial Intelligence.Québec: AAAI Press, 2014:1112 - 1119.
[3] SONG W, XIAO Z, WANG Y, et al.Session - based social recommendation via dynamic graph attention networks[C]//Proceedings of the Twelfth ACM International Conference on Web Search and Data Mining.New York: Association for Computing Machinery, 2019:555 - 563.
[4] NAVIGLI R, PONZETTO P, BABEINET S.Building a very large multilingual semantic network[C]//Proceedings of the 48th Annual Meeting of the Associationfor Computational Linguistics.Uppsala: Association for Computational Linguistics, 2010:216 - 225.
[5] JI S, PAN S, CAMBRIA E, et al.A survey on knowledge graphs: representation, acquisition, and applications[J]. IEEE T Neural Network, 2021,8(1):1 - 21.
[6] WANG Z, LV Q, LAN X, et al.Cross - lingual knowledge graph alignment via graph convolutional networks[C]//Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing.Brussels: EMNLP, 2018:349 - 357.
[7] JI G, HE S, XU L, et al.Knowledge graph embedding via dynamic mapping matrix[C]//Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing.Beijing: Association for Computational Linguistics, 2015:687 - 696.
[8] LIN Y, LIU Z, SUN M, et al.Learning entity and relation embeddings for knowledge graph completion[C]//Proceedings of the AAAI Conference on Artificial Intelligence.Austin, Texas: AAAI Press, 2015:2181 - 2187.
[9] CHEN M, TIAN Y, YANG M, et al.Multilingual knowledge graph embeddings for cross - lingual knowledge alignment[C]//Proceedings of the 26th International Joint Conference on Artificial Intelligence.Melbourne: AAAI Press, 2017:1511 - 1517.
备注/Memo
收稿日期: 2021-05-13
基金项目: 延边大学校企合作项目(延大科合字[2020]15号)
第一作者: 金城(1997—),男,硕士,研究方向为知识图谱与跨语言对齐.
通信作者: 崔荣一(1962—),男,博士,教授,研究方向为自然语言文本处理与模式识别.