{"type":"ScholarlyArticle","title":"BERT-INT:A BERT-based Interaction Model For Knowledge Graph Alignment","authors":[{"name":"Xiaobin Tang","slug":"xiaobin-tang","given":"Xiaobin","family":"Tang","affiliation":"Key Laboratory of Data Engineering and Knowledge Engineering of Ministry of Education , Renmin University of China; Information School , Renmin University of China"},{"name":"Jing Zhang","slug":"jing-zhang","given":"Jing","family":"Zhang","affiliation":"Key Laboratory of Data Engineering and Knowledge Engineering of Ministry of Education , Renmin University of China; Information School , Renmin University of China"},{"name":"Bo Chen","slug":"bo-chen","given":"Bo","family":"Chen","affiliation":"Key Laboratory of Data Engineering and Knowledge Engineering of Ministry of Education , Renmin University of China; Information School , Renmin University of China"},{"name":"Yang Yang","slug":"yang-yang","given":"Yang","family":"Yang","affiliation":"Zhejiang University"},{"name":"Hong Chen","slug":"hong-chen","given":"Hong","family":"Chen","affiliation":"Key Laboratory of Data Engineering and Knowledge Engineering of Ministry of Education , Renmin University of China; Information School , Renmin University of China"},{"name":"Cuiping Li","slug":"cuiping-li","given":"Cuiping","family":"Li","affiliation":"Key Laboratory of Data Engineering and Knowledge Engineering of Ministry of Education , Renmin University of China; Information School , Renmin University of China"}],"abstract":"Knowledge graph alignment aims to link equivalent entities across different knowledge graphs. To utilize both the graph structures and the side information such as name, description and attributes, most of the works propagate the side information especially names through linked entities by graph neural networks. However, due to the heterogeneity of different knowledge graphs, the alignment accuracy will be suffered from aggregating different neighbors. This work presents an interaction model to only leverage the side information. Instead of aggregating neighbors, we compute the interactions between neighbors which can capture fine-grained matches of neighbors. Similarly, the interactions of attributes are also modeled. Experimental results show that our model significantly outperforms the best state-of-the-art methods by 1.9-9.7% in terms of HitRatio@1 on the dataset DBP15K.","doi":"10.24963/ijcai.2020/439","url":"https://ijcai.org/proceedings/2020/439","pdf":"https://ijcai.org/proceedings/2020/0439.pdf","markdown":"https://ijcai.org/proceedings/2020/439.md","bibtex":"https://ijcai.org/proceedings/2020/bibtex/439","volume":{"slug":"2020","title":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2020","url":"https://ijcai.org/proceedings/2020/","year":2020,"location":"Yokohama","dates":"January 2021 (postponed from 11-17 July 2020)","editors":"Christian Bessiere","isbn":"978-0-9992411-6-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2020"},"section":"Machine Learning","track":"Main track","number":439,"pages":{"first":3174,"last":3180},"keywords":["Machine Learning: Knowledge-based Learning"],"videos":[{"label":"Video","url":"https://videos.ijcai20.org/24819/file_24819.m3u8","length_sec":284,"provider":"hls"}],"references":[{"position":1,"raw":"[Cao et al., 2019] Yixin Cao, Zhiyuan Liu, Chengjiang Li, Juanzi Li, and Tat-Seng Chua. Multi-channel graph neu- ral network for entity alignment. In ACL'19, pages 1452- 1461, 2019.","title":"Multi-channel graph neural network for entity alignment","authors":"Yixin Cao, Zhiyuan Liu, Chengjiang Li, Juanzi Li, Tat-Seng Chua","year":"2019","venue":"ACL'19","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Chen et al., 2017] Muhao Chen, Yingtao Tian, Mohan Yang, and Carlo Zaniolo. Multilingual knowledge graph embeddings for cross-lingual knowledge alignment. In IJ- CAI'17, pages 1511-1517, 2017.","title":"Multilingual knowledge graph embeddings for cross-lingual knowledge alignment","authors":"Chen","year":"2017","venue":"IJ-CAI'17","doi":null,"url":null,"internal_url":"/proceedings/2017/209"},{"position":3,"raw":"[Chen et al., 2018] Muhao Chen, Yingtao Tian, Kaiwei Chang, Steven Skiena, and Carlo Zaniolo. Co-training em- beddings of knowledge graphs and entity descriptions for cross-lingual entity alignment. In IJCAI'18, pages 3998- 4004, 2018.","title":"Co-training embeddings of knowledge graphs and entity descriptions for cross-lingual entity alignment","authors":"Chen","year":"2018","venue":"IJCAI'18","doi":null,"url":null,"internal_url":"/proceedings/2018/556"},{"position":4,"raw":"[Chen et al., 2020] Bo Chen, Jing Zhang, Xiaobin Tang, Hong Chen, and Cuiping Li. Jarka: Modeling attribute interactions for cross-lingual knowledge alignment. In PAKDD'20, 2020.","title":"Jarka: Modeling attribute interactions for cross-lingual knowledge alignment","authors":"Bo Chen, Jing Zhang, Xiaobin Tang, Hong Chen, Cuiping Li","year":"2020","venue":"PAKDD'20","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Conneau et al., 2018] Alexis Conneau, Guillaume Lample, Marc'Aurelio Ranzato, Ludovic Denoyer, and Hervé Jégou. Word translation without parallel data. In ICLR'18, 2018.","title":"Word translation without parallel data","authors":"Alexis Conneau, Guillaume Lample, Marc'aurelio Ranzato, Ludovic Denoyer, Hervé Jégou","year":"2018","venue":"ICLR'18","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Fey et al., 2020] Matthias Fey, Jan E. Lenssen, Christopher Morris, Jonathan Masci, and Nils M. Kriege. Deep graph matching consensus. In ICLR'20, 2020.","title":"Deep graph matching consensus","authors":"Matthias Fey, Jan E Lenssen, Christopher Morris, Jonathan Masci, Nils M Kriege","year":"2020","venue":"ICLR'20","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Guo et al., 2019] Lingbing Guo, Zequn Sun, and Wei Hu. Learning to exploit long-term relational dependencies in knowledge graphs. In ICML'19, 2019.","title":"Learning to exploit long-term relational dependencies in knowledge graphs","authors":"Guo","year":"2019","venue":"ICML'19","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Li et al., 2019] Chengjiang Li, Yixin Cao, Lei Hou, Jiaxin Shi, Juanzi Li, and Tat-Seng Chua. Semi-supervised en- tity alignment via joint knowledge embedding model and cross-graph model. In EMNLP'19, pages 2723-2732, 2019.","title":"Semi-supervised entity alignment via joint knowledge embedding model and cross-graph model","authors":"Chengjiang Li, Yixin Cao, Lei Hou, Jiaxin Shi, Juanzi Li, Tat-Seng Chua","year":"2019","venue":"EMNLP'19","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Lin et al., 2019] Xixun Lin, Hong Yang, Jia Wu, Chuan Zhou, and Bin Wang. Guiding cross-lingual entity align- ment via adversarial knowledge embedding. In ICDM'19, pages 429-438, 2019.","title":"Guiding cross-lingual entity alignment via adversarial knowledge embedding","authors":"Lin","year":"2019","venue":"ICDM'19","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Pei et al., 2019] Shichao Pei, Lu Yu, Robert Hoehndorf, and Xiangliang Zhang. Semi-supervised entity alignment via knowledge graph embedding with awareness of degree dif- ference. In WWW'19, pages 3130-3136, 2019.","title":"Semi-supervised entity alignment via knowledge graph embedding with awareness of degree difference","authors":"Pei","year":"2019","venue":"WWW'19","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Shi and Xiao, 2019] Xiaofei Shi and Yanghua Xiao. Mod- eling multi-mapping relations for precise cross-lingual en- tity alignment. In EMNLP'19, pages 813-822, 2019.","title":"Modeling multi-mapping relations for precise cross-lingual entity alignment","authors":"Xiaofei Shi, Yanghua Xiao","year":"2019","venue":"EMNLP'19","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Sun et al., 2017] Zequn Sun, Wei Hu, and Chengkai Li. Cross-lingual entity alignment via joint attribute- preserving embedding. In ISWC'17, pages 628-644, 2017.","title":"Cross-lingual entity alignment via joint attributepreserving embedding","authors":"Sun","year":"2017","venue":"ISWC'17","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Sun et al., 2018] Zequn Sun, Wei Hu, Qingheng Zhang, and Yuzhong Qu. Bootstrapping entity alignment with knowl- edge graph embedding. In IJCAI'18, pages 4396-4402, 2018.","title":"Bootstrapping entity alignment with knowledge graph embedding","authors":"Zequn Sun, Wei Hu, Qingheng Zhang, Yuzhong Qu","year":"2018","venue":"IJCAI'18","doi":null,"url":null,"internal_url":"/proceedings/2018/611"},{"position":14,"raw":"[Sun et al., 2019] Zequn Sun, Jiacheng Huang, Wei Hu, Muhao Chen, Lingbing Guo, and Yuzhong Qu. Transedge: Translating relation-contextualized embed- dings for knowledge graphs. In ISWC'19, pages 612-629, 2019.","title":"Transedge: Translating relation-contextualized embeddings for knowledge graphs","authors":"Sun","year":"2019","venue":"ISWC'19","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Sun et al., 2020] Zequn Sun, Chengming Wang, Wei Hu, Muhao Chen, Jian Dai, Wei Zhang, and Yuzhong Qu. Knowledge graph alignment network with gated multi-hop neighborhood aggregation. In AAAI'20, 2020.","title":"Knowledge graph alignment network with gated multi-hop neighborhood aggregation","authors":"Sun","year":"2020","venue":"AAAI'20","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Tong et al., 2019] Peihao Tong, Junjie Yao, Linzi He, and Liang Xu. Leveraging domain context for question an- swering over knowledge graph. Data Science and Engi- neering, 4:323-335, 2019.","title":"Leveraging domain context for question answering over knowledge graph","authors":"Tong","year":"2019","venue":"Data Science and Engineering","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Trsedya et al., 2019] Bayu Distiawan Trsedya, Jianzhong Qi, and Rui Zhang. Entity alignment between knowledge graphs using attribute embeddings. In AAAI'19, 2019.","title":"Entity alignment between knowledge graphs using attribute embeddings","authors":"Jianzhong Bayu Distiawan Trsedya, Rui Qi, Zhang","year":"2019","venue":"AAAI'19","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Wang et al., 2018] Zhichun Wang, Qingsong Lv, Xiaohan Lan, and Yu Zhang. Cross-lingual knowledge graph align- ment via graph convolutional networks. In EMNLP'18, pages 349-357, 2018.","title":"Cross-lingual knowledge graph alignment via graph convolutional networks","authors":"Zhichun Wang, Qingsong Lv, Xiaohan Lan, Yu Zhang","year":"2018","venue":"EMNLP'18","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Wu et al., 2019a] Yuting Wu, Xiao Liu, Yansong Feng, Zheng Wang, Rui Yan, and Dongyan Zhao. Relation- aware entity alignment for heterogeneous knowledge graphs. In IJCAI'19, pages 5278-5284, 2019.","title":"Relationaware entity alignment for heterogeneous knowledge graphs","authors":"Wu","year":"2019","venue":"IJCAI'19","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Wu et al., 2019b] Yuting Wu, Xiao Liu, Yansong Feng, Zheng Wang, and Dongyan Zhao. Jointly learning en- tity and relation representations for entity alignment. In EMNLP'19, pages 240-249, 2019.","title":"Jointly learning entity and relation representations for entity alignment","authors":"Wu","year":"2019","venue":"EMNLP'19","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Xiong et al., 2017] Chenyan Xiong, Zhuyun Dai, Jamie Callan, Zhiyuan Liu, and Russell Power. End-to-end neu- ral ad-hoc ranking with kernel pooling. In SIGIR'17, pages 55-64, 2017.","title":"End-to-end neural ad-hoc ranking with kernel pooling","authors":"Xiong","year":"2017","venue":"SIGIR'17","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Xu et al., 2019] Kun Xu, Liwei Wang, Mo Yu, Yansong Feng, Yan Song, Zhiguo Wang, and Dong Yu. Cross- lingual knowledge graph alignment via graph matching neural network. In ACL'19, pages 1452-1461, 2019.","title":"Crosslingual knowledge graph alignment via graph matching neural network","authors":"Kun Xu, Liwei Wang, Mo Yu, Yansong Feng, Yan Song, Zhiguo Wang, Dong Yu","year":"2019","venue":"ACL'19","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Yang et al., 2019] Hsiu-Wei Yang, Yanyan Zou, Peng Shi, Wei Lu, Jimmy Lin, and Xu Sun. Aligning cross-lingual entities with multi-aspect information. In EMNLP'19, pages 4430-4440, 2019.","title":"Aligning cross-lingual entities with multi-aspect information","authors":"Hsiu-Wei Yang, Yanyan Zou, Peng Shi, Wei Lu, Jimmy Lin, Xu Sun","year":"2019","venue":"EMNLP'19","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Ye et al., 2019] Rui Ye, Xin Li, Yujie Fang, Hongyu Zang, and Mingzhong Wang. A vectorized relational graph con- volutional network for multi-relational network alignment. In IJCAI'19, pages 4135-4141, 2019.","title":"A vectorized relational graph convolutional network for multi-relational network alignment","authors":"Rui Ye, Xin Li, Yujie Fang, Hongyu Zang, Mingzhong Wang","year":"2019","venue":"IJCAI'19","doi":null,"url":null,"internal_url":"/proceedings/2019/574"},{"position":25,"raw":"[Zeng et al., 2020] Wexin Zeng, Xiang Zhao, Jiuyang Tang, and Xuemin Lin. Ceaff:collective embedding-based entity alignment via adaptive features. In ICDE'20, 2020.","title":"Ceaff:collective embedding-based entity alignment via adaptive features","authors":"Wexin Zeng, Xiang Zhao, Jiuyang Tang, Xuemin Lin","year":"2020","venue":"ICDE'20","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Zhang et al., 2019] Qingheng Zhang, Zequn Sun, Wei Hu, Muhao Chen, Lingbing Guo, and Yuzhong Qu. Multi-view knowledge graph embedding for entity alignment. In IJ- CAI'19, pages 5429-5435, 2019.","title":"Multi-view knowledge graph embedding for entity alignment","authors":"Zhang","year":"2019","venue":"IJ-CAI'19","doi":null,"url":null,"internal_url":"/proceedings/2019/754"},{"position":27,"raw":"[Zhu et al., 2017] Hao Zhu, Ruobing Xie, Zhiyuan Liu, and Maosong Sun. Iterative entity alignment via joint knowl- edge embeddings. In IJCAI'17, pages 4258-4264, 2017.","title":"Iterative entity alignment via joint knowledge embeddings","authors":"Ruobing Hao Zhu, Zhiyuan Xie, Maosong Liu, Sun","year":"2017","venue":"IJCAI'17","doi":null,"url":null,"internal_url":"/proceedings/2017/595"},{"position":28,"raw":"[Zhu et al., 2019] Qiannan Zhu, Xiaofei Zhou, Jia Wu, Jian- long Tan, and Li Guo. Neighborhood-aware attentional representation for multilingual knowledge graphs. In IJ- CAI'19, pages 3231-3237, 2019.","title":"Neighborhood-aware attentional representation for multilingual knowledge graphs","authors":"Qiannan Zhu, Xiaofei Zhou, Jia Wu, Jianlong Tan, Li Guo","year":"2019","venue":"IJ-CAI'19","doi":null,"url":null,"internal_url":"/proceedings/2019/269"}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}