{"type":"ScholarlyArticle","title":"End-to-End Multi-Perspective Matching for Entity Resolution","authors":[{"name":"Cheng Fu","slug":"cheng-fu","given":"Cheng","family":"Fu","affiliation":"Chinese Information Processing Laboratory , Institute of Software , Chinese Academy of Sciences; University of Chinese Academy of Sciences"},{"name":"Xianpei Han","slug":"xianpei-han","given":"Xianpei","family":"Han","affiliation":"Chinese Information Processing Laboratory , Institute of Software , Chinese Academy of Sciences; State Key Laboratory of Computer Science , Institute of Software , Chinese Academy of Sciences"},{"name":"Le Sun","slug":"le-sun","given":"Le","family":"Sun","affiliation":"Chinese Information Processing Laboratory , Institute of Software , Chinese Academy of Sciences; State Key Laboratory of Computer Science , Institute of Software , Chinese Academy of Sciences"},{"name":"Bo Chen","slug":"bo-chen","given":"Bo","family":"Chen","affiliation":"Chinese Information Processing Laboratory , Institute of Software , Chinese Academy of Sciences"},{"name":"Wei Zhang","slug":"wei-zhang","given":"Wei","family":"Zhang","affiliation":"Alibaba Group , China"},{"name":"Suhui Wu","slug":"suhui-wu","given":"Suhui","family":"Wu","affiliation":"Alibaba Group , China"},{"name":"Hao Kong","slug":"hao-kong","given":"Hao","family":"Kong","affiliation":"Alibaba Group , China"}],"abstract":"Entity resolution (ER) aims to identify data records referring to the same real-world entity. Due to the heterogeneity of entity attributes and the diversity of similarity measures, one main challenge of ER is how to select appropriate similarity measures for different attributes. Previous ER methods usually employ heuristic similarity selection algorithms, which are highly specialized to specific ER problems and are hard to be generalized to other situations. Furthermore, previous studies usually perform similarity learning and similarity selection independently, which often result in error propagation and are hard to be optimized globally. To resolve the above problems, this paper proposes an end-to-end multi-perspective entity matching model, which can adaptively select optimal similarity measures for heterogenous attributes by jointly learning and selecting similarity measures in an end-to-end way. Experiments on two real-world datasets show that our method significantly outperforms previous ER methods.","doi":"10.24963/ijcai.2019/689","url":"https://ijcai.org/proceedings/2019/689","pdf":"https://ijcai.org/proceedings/2019/0689.pdf","markdown":"https://ijcai.org/proceedings/2019/689.md","bibtex":"https://ijcai.org/proceedings/2019/bibtex/689","volume":{"slug":"2019","title":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2019","url":"https://ijcai.org/proceedings/2019/","year":2019,"location":"Macao","dates":"10-16 August 2019","editors":"Sarit Kraus","isbn":"978-0-9992411-4-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2019"},"section":"Natural Language Processing","track":"Main track","number":689,"pages":{"first":4961,"last":4967},"keywords":["Natural Language Processing: Coreference Resolution","Multidisciplinary Topics and Applications: Databases","Natural Language Processing: Information Extraction"],"videos":[],"references":[{"position":1,"raw":"[Mudgal et al., 2018] Sidharth Mudga, Han Li, Theodoros Rekatsinas, AnHai Doan, Youngchoon Park, Ganesh Krishnan, Rohit Deep, Esteban Arcaute, and Vijay Raghavendra. Deep Learning for Entity Matching: A De- sign Space Exploration. In SIGMOD, 2018, pp. 19-34.","title":"Deep Learning for Entity Matching: A Design Space Exploration","authors":"Sidharth Mudga, Han Li, Theodoros Rekatsinas, Anhai Doan, Youngchoon Park, Ganesh Krishnan, Rohit Deep, Esteban Arcaute, Vijay Raghavendra","year":"2018","venue":"SIGMOD","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Ebraheem et al., 2018] Muhammad Ebraheem, Saravanan Thirumuruganathan, Shafiq Joty, Mourad Ouzzani, and Nan Tang. Distributed representations of tuples for entity resolution. PVLDB, 2018, 11(11): 1454-1467.","title":"Distributed representations of tuples for entity resolution","authors":"Ebraheem","year":"2018","venue":"PVLDB","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Köpcke et al., 2010] Hanna Köpcke, Andreas Thor, Erhard Rahm. Evaluation of entity resolution approaches on real- world match problems. PVLDB, 2010, 3(1-2): 484-493.","title":"Evaluation of entity resolution approaches on realworld match problems","authors":"Hanna Köpcke, Andreas Thor, Erhard Rahm","year":"2010","venue":"PVLDB","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Konda et al., 2016] Pradap Konda, Sanjib Dasl et al. Magel- lan: Toward building entity matching management sys- tems. PVLDB, 2016, 9(12): 1197-1208.","title":"Magellan: Toward building entity matching management systems","authors":"Konda","year":"2016","venue":"PVLDB","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Bojanowski et al., 2016] Piotr Bojanowski, Edouard Grave, Armand Joulin, Tomas Mikolov. Enriching Word Vectors with Subword Information. TACL, 2017, 5: 135-146.","title":"Enriching Word Vectors with Subword Information","authors":"Piotr Bojanowski, Edouard Grave, Armand Joulin, Tomas Mikolov","year":"2017","venue":"TACL","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Kingma and Ba, 2014] Diederik P. Kingma and Jimmy Lei Ba. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980, 2014.","title":"Adam: A method for stochastic optimization","authors":"P Diederik, Jimmy Lei Kingma, Ba","year":"2014","venue":null,"doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Srivastava et al., 2015] Rupesh Kumar Srivastava, Klaus Greff, and Jürgen Schmidhuber. Highway networks. In Proceedings of ICML, 2015.","title":"Highway networks","authors":"Rupesh Kumar Srivastava, Klaus Greff, Jürgen Schmidhuber","year":"2015","venue":"Proceedings of ICML","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Levenshtein, 1966] V. I. Levenshtein. Binary codes capable of correcting deletions, insertions, and reversals. Soviet physics doklady. 1966, 10(8): 707-710.","title":"Binary codes capable of correcting deletions, insertions, and reversals","authors":"V I Levenshtein","year":"1966","venue":"Soviet physics doklady","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"Jaro, 1980","title":null,"authors":"Jaro","year":"1980","venue":null,"doi":null,"url":null,"internal_url":null},{"position":10,"raw":"M. A. Jaro. UNIMATCH, a Record Linkage System: Users Manual. Bureau of the Census, 1980.","title":"UNIMATCH, a Record Linkage System: Users Manual","authors":"M A Jaro","year":"1980","venue":null,"doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Smith and Waterman, 1981] T. F. Smith and M. S. Water- man, Identification of Common Molecular Subsequences. Journal of molecular biology, 1981, 147(1): 195-197.","title":"Waterman, Identification of Common Molecular Subsequences","authors":"T F Smith, M S","year":"1981","venue":"Journal of molecular biology","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Wang et al., 2011] Jiannan Wang, Guoliang Li, Jeffrey Xu Yu, and Jianhua Feng. Entity matching: How similar is similar. PVLDB, 2011, 4(10): 622-633.","title":"Entity matching: How similar is similar","authors":"Jiannan Wang, Guoliang Li, Jeffrey Xu Yu, Jianhua Feng","year":"2011","venue":"PVLDB","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Elmagarmid et al., 2007] Ahmed K. Elmagarmid, Panagiotis G. Ipeirotis, and Vassilios S. Verykios. Duplicate record detection: A survey. Journal of TKDE, 2006, 19(1): 1-16.","title":"Duplicate record detection: A survey","authors":"Ahmed K Elmagarmid, G Panagiotis, Vassilios S Ipeirotis, Verykios","year":"2006","venue":"Journal of TKDE","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Christen, 2012] Peter Christen. A survey of indexing tech- niques for scalable record linkage and deduplication. Journal of TKDE, 2011, 24(9): 1537-1555.","title":"A survey of indexing techniques for scalable record linkage and deduplication","authors":"Christen Peter","year":"2011","venue":"Journal of TKDE","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Kong et al., 2016] Chao Kong, Ming Gao, Chen Xu, Wein- ing Qian, and Aoying Zhou. Entity matching across mul- tiple heterogeneous data sources. DASFAA, 2016. Springer, Cham, 2016, pp. 133-146.","title":"Entity matching across multiple heterogeneous data sources","authors":"Chao Kong, Ming Gao, Chen Xu, Weining Qian, Aoying Zhou","year":"2016","venue":"DASFAA","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Benjelloun et al., 2009] Omar Benjelloun, Hector Garcia- Molina, David Menestrina, Qi Su, Steven Euijong Whang, and Jennifer Widom. Swoosh: a generic approach to en- tity resolution. The VLDB Journal, 2009, 18(1): 255-276.","title":"Swoosh: a generic approach to entity resolution","authors":"Omar Benjelloun, Hector Garcia-Molina, David Menestrina, Qi Su, Steven Euijong Whang, Jennifer Widom","year":"2009","venue":"The VLDB Journal","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Bilke and Naumann, 2005] Alexander Bilke, Felix Nau- mann. Schema matching using duplicates. In Proceedings of ICDE, 2005, pp. 69-80.","title":"Schema matching using duplicates","authors":"Alexander Bilke, Felix Naumann","year":"2005","venue":"Proceedings of ICDE","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Koudas et al., 2004] Nick Koudas, Amit Marathe, and Divesh Srivastava, Flexible String Matching against Large Databases in Practice. PVLDB, 2004.","title":"Flexible String Matching against Large Databases in Practice","authors":"Nick Koudas, Amit Marathe, Divesh Srivastava","year":"2004","venue":"PVLDB","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Bilenko and Mooney, 2003] Mikhail Bilenko and Raymond J. Mooney. Adaptive duplicate detection using learnable string similarity measures. In SIGKDD, 2003, pp. 39-48.","title":"Adaptive duplicate detection using learnable string similarity measures","authors":"Mooney Bilenko, Mikhail Bilenko, Raymond J Mooney","year":"2003","venue":"SIGKDD","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Papadakis et al., 2016] George Papadakis, Jonathan Svirsky, Avigdor Gal, and Themis Palpanas. Comparative Analy- sis of Approximate Blocking Techniques for Entity Res- olution. PVLDB, 2016, 9(9): 684-695.","title":"Comparative Analysis of Approximate Blocking Techniques for Entity Resolution","authors":"George Papadakis, Jonathan Svirsky, Avigdor Gal, Themis Palpanas","year":"2016","venue":"PVLDB","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Sarawagi and Bhamidipaty, 2002] Sunita Sarawagi and Anuradha Bhamidipaty. Interactive deduplication using active learning. In SIGKDD, 2002, pp. 269-278.","title":"Interactive deduplication using active learning","authors":"Sunita Sarawagi, Anuradha Bhamidipaty","year":"2002","venue":"SIGKDD","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Cohen and Richman, 2002] William W. Cohen and Jacob Richman. Learning to match and cluster large high-di- mensional data sets for data integration. In SIGKDD, 2002, pp. 475-480.","title":"Learning to match and cluster large high-dimensional data sets for data integration","authors":"William W Cohen, Jacob Richman","year":"2002","venue":"SIGKDD","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Chaudhuri et al., 2007] Surajit Chaudhuri, Bee-Chung Chen, Venkatesh Ganti, and Raghav Kaushik. Example-driven design of efficient record matching queries. PVLDB, 2007, pp. 327-338","title":"Example-driven design of efficient record matching queries","authors":"Surajit Chaudhuri, Bee-Chung Chen, Venkatesh Ganti, Raghav Kaushik","year":"2007","venue":"PVLDB","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Sehgal et al., 2006] Vivek Sehgal, Lise Getoor, and Peter D Viechnicki. Entity resolution in geospatial data integra- tion. In ACM SIGSPATIAL, 2006, pp. 83-90.","title":"Entity resolution in geospatial data integration","authors":"Vivek Sehgal, Lise Getoor, Peter D Viechnicki","year":"2006","venue":"ACM SIGSPATIAL","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Singh et al., 2017] R Singh, V Meduri, A K Elmagarmid, S Madden, P Papotti, J Quiané-Ruiz, A Solar-Lezama, and N Tang. Synthesizing entity matching rules by examples. PVLDB, 2017, 11(2):189-202","title":"Synthesizing entity matching rules by examples","authors":"V Singh, A K Meduri, S Elmagarmid, P Madden, J Papotti, A Quiané-Ruiz, Solar-Lezama, Tang","year":"2017","venue":"PVLDB","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Hernández and Stolfo, 1995] Mauricio A. Hernández, Sal- vatore J. Stolfo. The merge/purge problem for large data- bases. ACM Sigmod Record. ACM, 1995, 24(2): 127-138.","title":"The merge/purge problem for large databases","authors":"Mauricio A Hernández, Salvatore J Stolfo","year":"1995","venue":"ACM Sigmod Record","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Arvind et al., 2009] Arvind Arasu, Christopher Ré, and Dan Suciu, Large-scale deduplication with constraints using dedupalog, In Proceedings of ICDE, 2009, pp. 952-963.","title":"Large-scale deduplication with constraints using dedupalog","authors":"Arvind Arasu, Christopher Ré, Dan Suciu","year":"2009","venue":"Proceedings of ICDE","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Fellegi et al., 1969] Ivan P. Fellegi and Alan B. Sunter. A theory for record linkage. Journal of the American Statis- tical Association, 64 (328):1183-1210, 1969.","title":"A theory for record linkage","authors":"Ivan P Fellegi, Alan B Sunter","year":"1969","venue":"Journal of the American Statistical Association","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Singla et al., 2006] Parag Singla and Pedro Domingos. En- tity resolution with markov logic. In ICDM, 2006.","title":"Entity resolution with markov logic","authors":"Parag Singla, Pedro Domingos","year":"2006","venue":"ICDM","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Firmani et al., 2016] Donatella Firmani, Barna Saha, and Divesh Srivastava. Online entity resolution using an ora- cle. PVLDB, 2016, 9(5): 384-395.","title":"Online entity resolution using an oracle","authors":"Donatella Firmani, Barna Saha, Divesh Srivastava","year":"2016","venue":"PVLDB","doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Nikolov et al., 2012] Andriy Nikolov, Mathieu d'Aquin, and Enrico Motta. Unsupervised learning of link discov- ery configuration. In ESWC, 2012.","title":"Unsupervised learning of link discovery configuration","authors":"Andriy Nikolov, Enrico Mathieu D'aquin, Motta","year":"2012","venue":"ESWC","doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Jurek et al., 2017] Anna Jurek, Jun Hong, Yuan Chi, Weiru Liu. A novel ensemble learning approach to unsupervised record linkage. Information Systems, 2017, 71: 40-54.","title":"A novel ensemble learning approach to unsupervised record linkage","authors":"Anna Jurek, Jun Hong, Yuan Chi, Weiru Liu","year":"2017","venue":"Information Systems","doi":null,"url":null,"internal_url":null},{"position":33,"raw":"[Jurek et al., 2018] Anna Jurek and Deepak P. It pays to be certain: unsupervised record linkage via ambiguity mini- mization. Pacific-Asia Conference on Knowledge Discov- ery and Data Mining, 2018.","title":"It pays to be certain: unsupervised record linkage via ambiguity minimization","authors":"Anna Jurek, P Deepak","year":"2018","venue":"Pacific-Asia Conference on Knowledge Discovery and Data Mining","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}