{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T10:44:44Z","timestamp":1772793884285,"version":"3.50.1"},"reference-count":51,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2013,7,18]],"date-time":"2013-07-18T00:00:00Z","timestamp":1374105600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["The VLDB Journal"],"published-print":{"date-parts":[[2013,10]]},"DOI":"10.1007\/s00778-013-0324-z","type":"journal-article","created":{"date-parts":[[2013,7,17]],"date-time":"2013-07-17T04:46:17Z","timestamp":1374036377000},"page":"665-687","source":"Crossref","is-referenced-by-count":66,"title":["Large-scale linked data integration using probabilistic reasoning and crowdsourcing"],"prefix":"10.1007","volume":"22","author":[{"given":"Gianluca","family":"Demartini","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Djellel Eddine","family":"Difallah","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Philippe","family":"Cudr\u00e9-Mauroux","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2013,7,18]]},"reference":[{"key":"324_CR1","doi-asserted-by":"crossref","unstructured":"Alonso, O., Baeza-Yates, R.A.: Design and implementation of relevance assessments using crowdsourcing. In: ECIR, pp. 153\u2013164 (2011).","DOI":"10.1007\/978-3-642-20161-5_16"},{"key":"324_CR2","unstructured":"Bailey, P., de Vries, A.P., Craswell, N., Soboroff, I.: Overview of the TREC 2007 enterprise track. In: TREC (2007)"},{"key":"324_CR3","unstructured":"Balog, K., Serdyukov, P., de Vries, A.P.: Overview of the TREC 2010 entity track. In: TREC (2010)"},{"key":"324_CR4","unstructured":"Banko, M., Cafarella, M.J., Soderland, S., Broadhead, M., Etzioni, O.: Open information extraction from the web. In: IJCAI, pp. 2670\u20132676 (2007)"},{"key":"324_CR5","doi-asserted-by":"crossref","unstructured":"Bilenko, M., Mooney, R.J.: Adaptive duplicate detection using learnable string similarity measures. In: Proceedings of the ninth ACM SIGKDD international conference on knowledge discovery and data mining, KDD \u201903, pp. 39\u201348. ACM, New York (2003). doi: 10.1145\/956750.956759","DOI":"10.1145\/956750.956759"},{"key":"324_CR6","doi-asserted-by":"crossref","unstructured":"Blanco, R., Halpin, H., Herzig, D., Mika, P., Pound, J., Thompson, H.S., Tran, D.T.: Repeatable and reliable search system evaluation using crowdsourcing. In: SIGIR, pp. 923\u2013932 (2011)","DOI":"10.1145\/2009916.2010039"},{"key":"324_CR7","doi-asserted-by":"crossref","unstructured":"Blanco, R., Mika, P., Vigna, S.: Effective and efficient entity search in RDF data. In: International Semantic Web Conference (ISWC), pp. 83\u201397 (2011)","DOI":"10.1007\/978-3-642-25073-6_6"},{"key":"324_CR8","doi-asserted-by":"crossref","unstructured":"Bouquet, P., Stoermer, H., Niederee, C., Mana, A.: Entity name system: the backbone of an open and scalable web of data. In: Proceedings of the IEEE International Conference on Semantic Computing (ICSC), pp. 554\u2013561 (2008)","DOI":"10.1109\/ICSC.2008.37"},{"key":"324_CR9","unstructured":"Bunescu, R., Pasca, M.: Using encyclopedic knowledge for named entity disambiguation. In: Proceedings of EACL, vol. 6 (2006)"},{"key":"324_CR10","unstructured":"Bunescu, R.C., Pasca, M.: Using encyclopedic knowledge for named entity disambiguation. In: EACL (2006)"},{"issue":"9","key":"324_CR11","doi-asserted-by":"crossref","first-page":"1537","DOI":"10.1109\/TKDE.2011.127","volume":"24","author":"P Christen","year":"2012","unstructured":"Christen, P.: A survey of indexing techniques for scalable record linkage and deduplication. IEEE Trans. Knowl. Data Eng. 24(9), 1537\u20131555 (2012). doi: 10.1109\/TKDE.2011.127","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"324_CR12","unstructured":"Ciaramita, M., Altun, Y.: Broad-coverage sense disambiguation and information extraction with a supersense sequence tagger. In: Proceedings of the 2006 Conference on Empirical Methods in Natural Language Processing, EMNLP \u201906, pp. 594\u2013602. ACL, Stroudsburg (2006). http:\/\/dl.acm.org\/citation.cfm?id=1610075.1610158"},{"key":"324_CR13","unstructured":"Cucerzan, S.: Large-scale named entity disambiguation based on Wikipedia data. In: Proceedings of EMNLP-CoNLL, vol. 2007, pp. 708\u2013716 (2007)"},{"key":"324_CR14","doi-asserted-by":"crossref","unstructured":"Cudr\u00e9-Mauroux, P., Aberer, K., Feher, A.: Probabilistic message passing in peer data management systems. In: International Conference on Data Engineering (ICDE) (2006)","DOI":"10.1109\/ICDE.2006.118"},{"key":"324_CR15","doi-asserted-by":"crossref","unstructured":"Cudr\u00e9-Mauroux, P., Haghani, P., Jost, M., Aberer, K., De Meer, H.: idMesh: graph-based disambiguation of linked data. In: WWW \u201909, pp. 591\u2013600. ACM, New York (2009). doi: 10.1145\/1526709.1526789","DOI":"10.1145\/1526709.1526789"},{"key":"324_CR16","unstructured":"Cunningham, H., Maynard, D., Bontcheva, K., Tablan, V.: GATE: A framework and graphical development environment for robust NLP tools and applications. In: Proceedings of the 40th Anniversary Meeting of the ACL (2002)"},{"key":"324_CR17","doi-asserted-by":"crossref","unstructured":"Demartini, G., Difallah, D.E., Cudr\u00e9-Mauroux, P.: Zencrowd: leveraging probabilistic reasoning and crowdsourcing techniques for large-scale entity linking. In: Proceedings of the 21st International Conference on World Wide Web, WWW \u201912, pp. 469\u2013478. ACM, New York (2012). doi: 10.1145\/2187836.2187900","DOI":"10.1145\/2187836.2187900"},{"key":"324_CR18","doi-asserted-by":"crossref","unstructured":"Demartini, G., Iofciu, T., de Vries, A.P.: Overview of the INEX 2009 entity ranking track. In: INEX, pp. 254\u2013264 (2009)","DOI":"10.1007\/978-3-642-14556-8_26"},{"key":"324_CR19","doi-asserted-by":"crossref","unstructured":"Dempster, A., Laird, N., Rubin, D.: Maximum likelihood from incomplete data via the EM algorithm. J. R. Stat. Soc. 39 (1977)","DOI":"10.1111\/j.2517-6161.1977.tb01600.x"},{"key":"324_CR20","doi-asserted-by":"crossref","unstructured":"Difallah, D.E., Demartini, G., Cudr\u00e9-Mauroux, P.: Pick-A-Crowd: Tell me what you like, and I\u2019ll tell you what to do. In: WWW\u201913. ACM, New York (2013)","DOI":"10.1145\/2488388.2488421"},{"key":"324_CR21","doi-asserted-by":"crossref","unstructured":"Dong, X., Halevy, A., Madhavan, J.: Reference reconciliation in complex information spaces. In: SIGMOD, pp. 85\u201396. ACM, New York (2005)","DOI":"10.1145\/1066157.1066168"},{"issue":"11","key":"324_CR22","first-page":"1387","volume":"4","author":"A Feng","year":"2011","unstructured":"Feng, A., Franklin, M.J., Kossmann, D., Kraska, T., Madden, S., Ramesh, S., Wang, A., Xin, R.: CrowdDB: Query Processing with the VLDB Crowd. PVLDB 4(11), 1387\u20131390 (2011)","journal-title":"PVLDB"},{"key":"324_CR23","unstructured":"Finin, T., Murnane, W., Karandikar, A., Keller, N., Martineau, J., Dredze, M.: Annotating named entities in Twitter data with crowdsourcing. In: Proceedings of the NAACL HLT 2010 Workshop on Creating Speech and Language Data with Amazon\u2019s Mechanical Turk, CSLDAMT \u201910, pp. 80\u201388 (2010)"},{"key":"324_CR24","doi-asserted-by":"crossref","unstructured":"Getoor, L., Machanavajjhala, A.: Entity resolution: tutorial. In: VLDB (2012)","DOI":"10.14778\/2367502.2367564"},{"key":"324_CR25","doi-asserted-by":"crossref","unstructured":"Haas, K., Mika, P., Tarjan, P., Blanco, R.: Enhanced results for web search. In: SIGIR, pp. 725\u2013734 (2011)","DOI":"10.1145\/2009916.2010014"},{"key":"324_CR26","doi-asserted-by":"crossref","unstructured":"Han, X., Zhao, J.: Named entity disambiguation by leveraging wikipedia semantic knowledge. In: Proceeding of the 18th ACM Conference on Information and Knowledge Management, CIKM \u201909, pp. 215\u2013224. ACM, New York (2009). doi: 10.1145\/1645953.1645983","DOI":"10.1145\/1645953.1645983"},{"issue":"406","key":"324_CR27","doi-asserted-by":"crossref","first-page":"414","DOI":"10.1080\/01621459.1989.10478785","volume":"84","author":"M Jaro","year":"1989","unstructured":"Jaro, M.: Advances in record-linkage methodology as applied to matching the 1985 census of Tampa. Florida. J. Am. Stat. Assoc. 84(406), 414\u2013420 (1989)","journal-title":"Florida. J. Am. Stat. Assoc."},{"key":"324_CR28","doi-asserted-by":"crossref","unstructured":"Kazai, G.: In search of quality in crowdsourcing for search engine evaluation. In: ECIR, pp. 165\u2013176 (2011)","DOI":"10.1007\/978-3-642-20161-5_17"},{"key":"324_CR29","doi-asserted-by":"crossref","unstructured":"Kazai, G., Kamps, J., Koolen, M., Milic-Frayling, N.: Crowdsourcing for book search evaluation: impact of hit design on comparative system ranking. In: SIGIR, pp. 205\u2013214 (2011)","DOI":"10.1145\/2009916.2009947"},{"key":"324_CR30","doi-asserted-by":"crossref","unstructured":"Klein, D., Manning, C.: Accurate unlexicalized parsing. In: Proceedings of the 41st Annual Meeting on Association for Computational Linguistics, vol. 1, pp. 423\u2013430 (2003)","DOI":"10.3115\/1075096.1075150"},{"key":"324_CR31","doi-asserted-by":"crossref","unstructured":"Kohlsch\u00fctter, C., Fankhauser, P., Nejdl, W.: Boilerplate detection using shallow text features. In: WSDM, pp. 441\u2013450 (2010)","DOI":"10.1145\/1718487.1718542"},{"key":"324_CR32","doi-asserted-by":"crossref","unstructured":"Kschischang, F., Frey, B., Loeliger, H.A.: Factor graphs and the sum-product algorithm. IEEE Trans. Inform. Theory 47(2) (2001)","DOI":"10.1109\/18.910572"},{"key":"324_CR33","unstructured":"Levenshtein, V.: Binary codes capable of correcting deletions, insertions, and reversals. In: Soviet Physics Doklady, vol. 10, pp. 707\u2013710 (1966)"},{"issue":"12","key":"324_CR34","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/0020-0255(95)00185-9","volume":"89","author":"EP Lim","year":"1996","unstructured":"Lim, E.P., Srivastava, J., Prabhakar, S., Richardson, J.: Entity identification in database integration. Inform. Sci. 89(12), 1\u201338 (1996). doi: 10.1016\/0020-0255(95)00185-9","journal-title":"Inform. Sci."},{"key":"324_CR35","doi-asserted-by":"crossref","unstructured":"Liu, X., Lu, M., Ooi, B.C., Shen, Y., Wu, S., Zhang, M.: Cdas: a crowdsourcing data analytics system. Proc. VLDB Endow. 5(10), 1040\u20131051 (2012). http:\/\/dl.acm.org\/citation.cfm?id=2336664.2336676","DOI":"10.14778\/2336664.2336676"},{"issue":"1","key":"324_CR36","first-page":"13","volume":"5","author":"A Marcus","year":"2011","unstructured":"Marcus, A., Wu, E., Karger, D.R., Madden, S., Miller, R.C.: Human-powered sorts and joins. PVLDB 5(1), 13\u201324 (2011)","journal-title":"PVLDB"},{"key":"324_CR37","doi-asserted-by":"crossref","unstructured":"Mendes, P.N., Jakob, M., Garc\u00eda-Silva, A., Bizer, C.: DBpedia spotlight: shedding light on the web of documents. In: Proceedings of the 7th International Conference on Semantic Systems (I-Semantics) (2011)","DOI":"10.1145\/2063518.2063519"},{"key":"324_CR38","doi-asserted-by":"crossref","unstructured":"Mihalcea, R., Csomai, A.: Wikify!: linking documents to encyclopedic knowledge. In: Proceedings of the Sixteenth ACM Conference on Conference on Information and Knowledge Management, CIKM \u201907, pp. 233\u2013242. ACM, New York (2007). doi: 10.1145\/1321440.1321475","DOI":"10.1145\/1321440.1321475"},{"key":"324_CR39","unstructured":"Murphy, K.M., Weiss, Y., Jordan, M.I.: Loopy belief propagation for approximate inference: an empirical study. In: Uncertainty in Artificial Intelligence (UAI) (1999)"},{"key":"324_CR40","doi-asserted-by":"crossref","unstructured":"On, B., Koudas, N., Lee, D., Srivastava, D.: Group linkage. In: Proceedings of the 23rd IEEE International Conference on Data Engineering (ICDE), pp. 496\u2013505 (2007)","DOI":"10.1109\/ICDE.2007.367895"},{"key":"324_CR41","doi-asserted-by":"crossref","unstructured":"Papadakis, G., Ioannou, E., Nieder\u00e9e, C., Palpanas, T., Nejdl, W.: Beyond 100 million entities: large-scale blocking-based resolution for heterogeneous data. In: Proceedings of the Fifth ACM International Conference on Web Search and Data Mining, WSDM \u201912, pp. 53\u201362. ACM, New York (2012). doi: 10.1145\/2124295.2124305","DOI":"10.1145\/2124295.2124305"},{"key":"324_CR42","doi-asserted-by":"crossref","unstructured":"Pound, J., Mika, P., Zaragoza, H.: Ad-hoc object retrieval in the web of data. In: WWW, pp. 771\u2013780 (2010)","DOI":"10.1145\/1772690.1772769"},{"key":"324_CR43","doi-asserted-by":"crossref","unstructured":"Selke, J., Lofi, C., Balke, W.T.: Pushing the boundaries of crowd-enabled databases with query-driven schema expansion. Proc. VLDB Endow. 5(6), 538\u2013549 (2012). http:\/\/dl.acm.org\/citation.cfm?id=2168651.2168655","DOI":"10.14778\/2168651.2168655"},{"key":"324_CR44","doi-asserted-by":"crossref","unstructured":"Shen, W., Wang, J., Luo, P., Wang, M.: Liege: link entities in web lists with knowledge base. In: Proceedings of the 18th ACM SIGKDD international conference on Knowledge discovery and data mining, KDD \u201912, pp. 1424\u20131432. ACM, New York (2012). doi: 10.1145\/2339530.2339753","DOI":"10.1145\/2339530.2339753"},{"key":"324_CR45","doi-asserted-by":"crossref","unstructured":"Tonon, A., Demartini, G., Cudr\u00e9-Mauroux, P.: Combining inverted indices and structured search for ad-hoc object retrieval. In: Proceedings of the 35th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR \u201912, pp. 125\u2013134. ACM, New York (2012). doi: 10.1145\/2348283.2348304","DOI":"10.1145\/2348283.2348304"},{"issue":"8","key":"324_CR46","doi-asserted-by":"crossref","first-page":"58","DOI":"10.1145\/1378704.1378719","volume":"51","author":"L Ahn von","year":"2008","unstructured":"von Ahn, L., Dabbish, L.: Designing games with a purpose. Commun. ACM 51(8), 58\u201367 (2008). doi: 10.1145\/1378704.1378719","journal-title":"Commun. ACM"},{"key":"324_CR47","doi-asserted-by":"crossref","unstructured":"von Ahn, L., Liu, R., Blum, M.: Peekaboom: a game for locating objects in images. In: Proceedings of the SIGCHI Conference on Human Factors in Computing Systems, CHI \u201906, pp. 55\u201364. ACM, New York (2006). doi: 10.1145\/1124772.1124782","DOI":"10.1145\/1124772.1124782"},{"issue":"11","key":"324_CR48","first-page":"1483","volume":"5","author":"J Wang","year":"2012","unstructured":"Wang, J., Kraska, T., Franklin, M.J., Feng, J.: CrowdER: crowdsourcing entity resolution. PVLDB 5(11), 1483\u20131494 (2012)","journal-title":"PVLDB"},{"key":"324_CR49","doi-asserted-by":"crossref","unstructured":"Whang, S.E., Menestrina, D., Koutrika, G., Theobald, M., Garcia-Molina, H.: Entity resolution with iterative blocking. In: Proceedings of the 2009 ACM SIGMOD International Conference on Management of data, SIGMOD \u201909, pp. 219\u2013232. ACM, New York (2009). doi: 10.1145\/1559845.1559870","DOI":"10.1145\/1559845.1559870"},{"key":"324_CR50","unstructured":"Winkler, W.: The state of record linkage and current research problems. US Census Bureau. In: Statistical Research Division (1999)"},{"key":"324_CR51","doi-asserted-by":"crossref","unstructured":"Wylot, M., Pont, J., Wisniewski, M., Cudr\u00e9-Mauroux, P.: dipLODocus[RDF]\u2014short and long-tail rdf analytics for massive webs of data. In: International Semantic Web Conference (ISWC), pp. 778\u2013793 (2011)","DOI":"10.1007\/978-3-642-25073-6_49"}],"container-title":["The VLDB Journal"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00778-013-0324-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00778-013-0324-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00778-013-0324-z","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,7,18]],"date-time":"2019-07-18T14:18:43Z","timestamp":1563459523000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00778-013-0324-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,7,18]]},"references-count":51,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2013,10]]}},"alternative-id":["324"],"URL":"https:\/\/doi.org\/10.1007\/s00778-013-0324-z","relation":{},"ISSN":["1066-8888","0949-877X"],"issn-type":[{"value":"1066-8888","type":"print"},{"value":"0949-877X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2013,7,18]]}}}