{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,11]],"date-time":"2026-01-11T05:39:36Z","timestamp":1768109976525,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":74,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,6,10]],"date-time":"2022-06-10T00:00:00Z","timestamp":1654819200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Alfred P. Sloan Fellowship"},{"name":"NSF","award":["2127309,1652303, 1909046"],"award-info":[{"award-number":["2127309,1652303, 1909046"]}]},{"name":"HDR TRIPODS","award":["1934846"],"award-info":[{"award-number":["1934846"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,6,10]]},"DOI":"10.1145\/3514221.3526147","type":"proceedings-article","created":{"date-parts":[[2022,6,12]],"date-time":"2022-06-12T02:33:49Z","timestamp":1655001229000},"page":"414-428","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Hierarchical Entity Resolution using an Oracle"],"prefix":"10.1145","author":[{"given":"Sainyam","family":"Galhotra","sequence":"first","affiliation":[{"name":"University of Chicago, Chicago, IL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Donatella","family":"Firmani","sequence":"additional","affiliation":[{"name":"Sapienza University, Rome, UNK, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Barna","family":"Saha","sequence":"additional","affiliation":[{"name":"University of California, San Diego, San Diego, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Divesh","family":"Srivastava","sequence":"additional","affiliation":[{"name":"AT&T Chief Data Office, Bedminster, NJ, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2022,6,11]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Dmoz https:\/\/dmoz-odp.org\/."},{"key":"e_1_3_2_1_2_1","unstructured":"Google vision api https:\/\/cloud.google.com\/vision."},{"key":"e_1_3_2_1_3_1","unstructured":"Scikit-learn https:\/\/scikit-learn.org\/stable\/modules\/clustering.html."},{"key":"e_1_3_2_1_4_1","unstructured":"World cities database https:\/\/simplemaps.com\/data\/world-cities."},{"key":"e_1_3_2_1_5_1","volume-title":"How to design robust algorithms using noisy comparison oracle. arXiv preprint arXiv:2105.05782","author":"Addanki Raghavendra","year":"2021","unstructured":"Raghavendra Addanki, Sainyam Galhotra, and Barna Saha. How to design robust algorithms using noisy comparison oracle. arXiv preprint arXiv:2105.05782, 2021."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1137\/0210030"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P14-1098"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.5555\/2936924.2937066"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-48224-5_12"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-21458-5_14"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3318464.3389742"},{"key":"e_1_3_2_1_12_1","volume-title":"Hierarchical clustering with structural constraints. arXiv preprint arXiv:1805.09476","author":"Chatziafratis Vaggos","year":"2018","unstructured":"Vaggos Chatziafratis, Rad Niazadeh, and Moses Charikar. Hierarchical clustering with structural constraints. arXiv preprint arXiv:1805.09476, 2018."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2015.2462357"},{"key":"e_1_3_2_1_14_1","first-page":"378","volume-title":"Proceedings of the Twenty-Ninth Annual ACM-SIAM Symposium on Discrete Algorithms","author":"Cohen-Addad Vincent","year":"2018","unstructured":"Vincent Cohen-Addad, Varun Kanade, Frederik Mallmann-Trenn, and Claire Mathieu. Hierarchical clustering: Objective functions and algorithms. In Proceedings of the Twenty-Ninth Annual ACM-SIAM Symposium on Discrete Algorithms, pages 378--397. SIAM, 2018."},{"key":"e_1_3_2_1_15_1","volume-title":"Donatella Firmani, Maurizio Mazzei, Paolo Merialdo, Federico Piai, and Divesh Srivastava. Alaska: A flexible benchmark for data integration tasks","author":"Crescenzi Valter","year":"2021","unstructured":"Valter Crescenzi, Andrea De Angelis, Donatella Firmani, Maurizio Mazzei, Paolo Merialdo, Federico Piai, and Divesh Srivastava. Alaska: A flexible benchmark for data integration tasks, 2021."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/2897518.2897527"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/2684066"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.2200\/S00578ED1V01Y201404DTM040"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3183713.3199672"},{"issue":"11","key":"e_1_3_2_1_20_1","first-page":"1454","article-title":"Distributed representations of tuples for entity resolution","volume":"11","author":"Ebraheem Muhammad","year":"2018","unstructured":"Muhammad Ebraheem, Saravanan Thirumuruganathan, Shafiq Joty, Mourad Ouzzani, and Nan Tang. Distributed representations of tuples for entity resolution. PVLDB, 11(11):1454--1467, 2018.","journal-title":"PVLDB"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.5555\/3174304.3175295"},{"key":"e_1_3_2_1_22_1","first-page":"260","volume-title":"Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics","author":"Eriksson Brian","year":"2011","unstructured":"Brian Eriksson, Gautam Dasarathy, Aarti Singh, and Rob Nowak. Active clustering: Robust and efficient hierarchical clustering using adaptively selected similarities. In Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, pages 260--268, 2011."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1969.10501049"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.14778\/2876473.2876474"},{"key":"e_1_3_2_1_25_1","unstructured":"Sainyam Galhotra Donatella Firmani Barna Saha and Divesh Srivastava. Hierarchical entity resolution using an oracle. In https:\/\/hierarchicaler.github.io ."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3183713.3183755"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00778-021-00656-7"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.14778\/2367502.2367564"},{"key":"e_1_3_2_1_29_1","first-page":"7454","volume-title":"Advances in Neural Information Processing Systems","author":"Ghoshdastidar Debarghya","year":"2019","unstructured":"Debarghya Ghoshdastidar, Micha\u00ebl Perrot, and Ulrike von Luxburg. Foundations of comparison-based hierarchical clustering. In Advances in Neural Information Processing Systems, pages 7454--7464, 2019."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/2588555.2588576"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1016\/0304-3975(85)90224-5"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1002\/rsa.20372"},{"key":"e_1_3_2_1_33_1","volume-title":"Fault-tolerant entity resolution with the crowd","author":"Gruenheid Anja","year":"2015","unstructured":"Anja Gruenheid, Besmira Nushi, Tim Kraska, Wolfgang Gatterbauer, and Donald Kossmann. Fault-tolerant entity resolution with the crowd, 2015."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/2213836.2213880"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3132847.3133041"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/2872427.2883037"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.3115\/992133.992154"},{"key":"e_1_3_2_1_38_1","volume-title":"reliable active classification with comparison queries. arXiv preprint arXiv:2001.05497","author":"Hopkins Max","year":"2020","unstructured":"Max Hopkins, Daniel Kane, Shachar Lovett, and Gaurav Mahajan. Noise-tolerant, reliable active classification with comparison queries. arXiv preprint arXiv:2001.05497, 2020."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3289600.3290972"},{"key":"e_1_3_2_1_40_1","volume-title":"Metric learning for individual fairness. arXiv preprint arXiv:1906.00250","author":"Ilvento Christina","year":"2019","unstructured":"Christina Ilvento. Metric learning for individual fairness. arXiv preprint arXiv:1906.00250, 2019."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1006\/jagm.1996.0035"},{"key":"e_1_3_2_1_42_1","volume-title":"Comparison based learning from weak oracles. arXiv preprint arXiv:1802.06942","author":"Kazemi Ehsan","year":"2018","unstructured":"Ehsan Kazemi, Lin Chen, Sanjoy Dasgupta, and Amin Karbasi. Comparison based learning from weak oracles. arXiv preprint arXiv:1802.06942, 2018."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-23719-5_62"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3035918.3035953"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.5555\/1870658.1870766"},{"key":"e_1_3_2_1_46_1","volume-title":"Deep entity matching with pre-trained language models. arXiv preprint arXiv:2004.00584","author":"Li Yuliang","year":"2020","unstructured":"Yuliang Li, Jinfeng Li, Yoshihiko Suhara, AnHai Doan, and Wang-Chiew Tan. Deep entity matching with pre-trained language models. arXiv preprint arXiv:2004.00584, 2020."},{"key":"e_1_3_2_1_47_1","volume-title":"Hierarchical text classification with reinforced label assignment. arXiv preprint arXiv:1908.10419","author":"Mao Yuning","year":"2019","unstructured":"Yuning Mao, Jingjing Tian, Jiawei Han, and Xiang Ren. Hierarchical text classification with reinforced label assignment. arXiv preprint arXiv:1908.10419, 2019."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403274"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3183713.3196926"},{"key":"e_1_3_2_1_50_1","unstructured":"Roberto Navigli Paola Velardi and Stefano Faralli. A graph-based algorithm for inducing lexical taxonomies from scratch."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF02614365"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/S16-1206"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.14778\/2947618.2947624"},{"key":"e_1_3_2_1_54_1","first-page":"25","volume-title":"WebDB","author":"Polychronopoulos Vassilis","year":"2013","unstructured":"Vassilis Polychronopoulos, Luca De Alfaro, James Davis, Hector Garcia-Molina, and Neoklis Polyzotis. Human-powered top-k lists. In WebDB, pages 25--30, 2013."},{"key":"e_1_3_2_1_55_1","unstructured":"Cristina Roquet S\u00e9bastien Lavergne and Wilfried Thuiller. One tree to link them all: a phylogenetic dataset for the european tetrapoda. PLoS currents 6."},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220115"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.5555\/3104482.3104567"},{"key":"e_1_3_2_1_58_1","volume-title":"Towards a practical o (n logn) phylogeny algorithm. Algorithms for molecular biology, 7(1):32","author":"Truszkowski Jakub","year":"2012","unstructured":"Jakub Truszkowski, Yanqi Hao, and Daniel G Brown. Towards a practical o (n logn) phylogeny algorithm. Algorithms for molecular biology, 7(1):32, 2012."},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2017.148"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1162\/COLI_a_00146"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1145\/2187836.2187969"},{"key":"e_1_3_2_1_62_1","first-page":"289","volume-title":"Combinatorial Algorithms: 31st International Workshop, IWOCA 2020, Bordeaux, France, June 8--10, 2020","author":"Verdugo Victor","unstructured":"Victor Verdugo. Skyline computation with noisy comparisons. In Combinatorial Algorithms: 31st International Workshop, IWOCA 2020, Bordeaux, France, June 8--10, 2020, Proceedings, page 289. Springer."},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2015.7113286"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1145\/3035918.3035931"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.14778\/2732977.2732982"},{"key":"e_1_3_2_1_66_1","volume-title":"Crowder: Crowdsourcing entity resolution. arXiv preprint arXiv:1208.1927","author":"Wang Jiannan","year":"2012","unstructured":"Jiannan Wang, Tim Kraska, Michael J Franklin, and Jianhua Feng. Crowder: Crowdsourcing entity resolution. arXiv preprint arXiv:1208.1927, 2012."},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1145\/2566486.2568037"},{"key":"e_1_3_2_1_68_1","volume-title":"The multidimensional wisdom of crowds. Advances in neural information processing systems, 23:2424--2432","author":"Welinder Peter","year":"2010","unstructured":"Peter Welinder, Steve Branson, Pietro Perona, and Serge Belongie. The multidimensional wisdom of crowds. Advances in neural information processing systems, 23:2424--2432, 2010."},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.14778\/2536336.2536337"},{"key":"e_1_3_2_1_70_1","doi-asserted-by":"publisher","DOI":"10.1145\/2213836.2213891"},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.14778\/3275536.3275541"},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220064"},{"key":"e_1_3_2_1_73_1","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380017"},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313578"}],"event":{"name":"SIGMOD\/PODS '22: International Conference on Management of Data","location":"Philadelphia PA USA","acronym":"SIGMOD\/PODS '22","sponsor":["SIGMOD ACM Special Interest Group on Management of Data"]},"container-title":["Proceedings of the 2022 International Conference on Management of Data"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3514221.3526147","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3514221.3526147","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3514221.3526147","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T18:10:13Z","timestamp":1750183813000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3514221.3526147"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6,10]]},"references-count":74,"alternative-id":["10.1145\/3514221.3526147","10.1145\/3514221"],"URL":"https:\/\/doi.org\/10.1145\/3514221.3526147","relation":{},"subject":[],"published":{"date-parts":[[2022,6,10]]},"assertion":[{"value":"2022-06-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}