{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,16]],"date-time":"2025-02-16T16:10:02Z","timestamp":1739722202046,"version":"3.37.1"},"reference-count":51,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2010,1,9]],"date-time":"2010-01-09T00:00:00Z","timestamp":1262995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2010,1,9]],"date-time":"2010-01-09T00:00:00Z","timestamp":1262995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Inf Retrieval"],"published-print":{"date-parts":[[2010,10]]},"DOI":"10.1007\/s10791-009-9125-9","type":"journal-article","created":{"date-parts":[[2010,1,8]],"date-time":"2010-01-08T06:24:04Z","timestamp":1262931844000},"page":"568-600","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":20,"title":["Entity ranking in Wikipedia: utilising categories, links and topic difficulty prediction"],"prefix":"10.1007","volume":"13","author":[{"given":"Jovan","family":"Pehcevski","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"James A.","family":"Thom","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anne-Marie","family":"Vercoustre","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vladimir","family":"Naumovski","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2010,1,9]]},"reference":[{"key":"9125_CR1","doi-asserted-by":"crossref","unstructured":"Adelberg, B., & Denny, M. (1999). Nodose version 2.0. In Proceedings of the 1999 ACM SIGMOD international conference on management of data (SIGMOD\u201999), Philadelphia, Pennsylvania, pp. 559\u2013561.","DOI":"10.1145\/304182.304576"},{"key":"9125_CR2","doi-asserted-by":"crossref","unstructured":"Awang Iskandar, D., Pehcevski, J., Thom, J. A., & Tahaghoghi, S. M. M. (2007). Social media retrieval using image features and structured text. In Comparative evaluation of XML information retrieval systems: Fifth workshop of the INitiative for the evaluation of XML retrieval, INEX 2006, Lecture notes in computer science, Vol. 4518, pp. 358\u2013372.","DOI":"10.1007\/978-3-540-73888-6_35"},{"key":"9125_CR3","doi-asserted-by":"crossref","unstructured":"Bast, H., Chitea, A., Suchanek, F., & Weber, I. (2007). ESTER: Efficient search on text, entities, and relations. In Proceedings of the 30th ACM international conference on research and development in information retrieval (SIGIR\u201907), Amsterdam, The Netherlands, pp. 671\u2013678.","DOI":"10.1145\/1277741.1277856"},{"key":"9125_CR4","unstructured":"Blanchard, E., Harzallah, M., & Henri Briand, P. K. (2005). A typology of ontology-based semantic measures. In Proceedings of the open interop workshop on enterprise modelling and ontologies for interoperability (EMOI-INTEROP\u201905), Porto, Portugal. http:\/\/www.sunsite.informatik.rwth-aachen.de\/Publications\/CEUR-WS\/Vol-160\/paper26.pdf."},{"issue":"1","key":"9125_CR5","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","volume":"45","author":"L. Breiman","year":"2001","unstructured":"Breiman, L. (2001). Random forests. Machine Learning 45(1), 5\u201332","journal-title":"Machine Learning"},{"key":"9125_CR6","doi-asserted-by":"crossref","unstructured":"Brin, S., & Page, L. (1998). The anatomy of a large-scale hypertextual Web search engine. In Proceedings of the 7th international conference on world wide web, Brisbane, Australia, pp. 107\u2013117.","DOI":"10.1016\/S0169-7552(98)00110-X"},{"key":"9125_CR7","doi-asserted-by":"crossref","unstructured":"Cai, D., He, X., Wen, J. R., & Ma, W. Y. (2004). Block-level link analysis. In Proceedings of the 27th ACM international conference on research and development in information retrieval (SIGIR\u201904), Sheffield, UK, pp. 440\u2013447.","DOI":"10.1145\/1008992.1009068"},{"key":"9125_CR8","doi-asserted-by":"crossref","unstructured":"Callan, J., & Mitamura, T. (2002). Knowledge-based extraction of named entities. In Proceedings of the 11th ACM conference on information and knowledge management (CIKM\u201902), McLean, Virginia, pp. 532\u2013537.","DOI":"10.1145\/584792.584880"},{"issue":"2","key":"9125_CR9","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1145\/1113343.1113349","volume":"39","author":"D. Carmel","year":"2005","unstructured":"Carmel, D., Yom-Tov, E., & Soboroff, I. (2005). Predicting query difficulty\u2014methods and applications. SIGIR Forum 39(2), 25\u201328.","journal-title":"SIGIR Forum"},{"key":"9125_CR10","doi-asserted-by":"crossref","unstructured":"Cronen-Townsend, S., Zhou, Y., & Croft, W. B. (2002). Predicting query performance. In Proceedings of the 25th ACM SIGIR conference on research and development in information retrieval (SIGIR\u201902), Tampere, Finland, pp. 299\u2013306.","DOI":"10.1145\/564376.564429"},{"key":"9125_CR11","unstructured":"Cucerzan, S. (2007). Large-scale named entity disambiguation based on Wikipedia data. In Proceedings of the 2007 joint conference on EMNLP and CoNLL, Prague, The Czech Republic, pp. 708\u2013716."},{"key":"9125_CR12","unstructured":"Cucerzan, S., & Yarowsky, D. (1999). Language independent named entity recognition combining morphological and contextual evidence. In Proceedings of the 1999 joint SIGDAT conference on EMNLP and VLC, Maryland, MD, pp. 90\u201399."},{"key":"9125_CR46","doi-asserted-by":"crossref","unstructured":"de Vries A. P., Vercoustre A. M., Thom J. A., Craswell N., & Lalmas M. (2008). Overview of the INEX 2007 entity ranking track. In Focused access to XML documents: Sixth international workshop of the initiative for the evaluation of XML retrieval, INEX 2007, Lecture notes in computer science, Vol. 4862, pp. 1\u201323.","DOI":"10.1007\/978-3-540-85902-4_22"},{"key":"9125_CR13","doi-asserted-by":"crossref","unstructured":"Demartini, G., de Vries, A. P., Iofciu, T., & Zhu, J. (2009). Overview of the INEX 2008 entity ranking track. In Advances in focused retrieval: Seventh international workshop of the initiative for the evaluation of XML retrieval, INEX 2008, Lecture notes in computer science, Vol. 5631.","DOI":"10.1007\/978-3-642-03761-0_25"},{"issue":"1","key":"9125_CR14","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1145\/1147197.1147210","volume":"40","author":"L. Denoyer","year":"2006","unstructured":"Denoyer, L., & Gallinari, P. (2006). The Wikipedia XML corpus. SIGIR Forum 40(1), 64\u201369","journal-title":"SIGIR Forum"},{"key":"9125_CR15","unstructured":"Ehrig, M., Haase, P., Stojanovic, N., & Hefke, M. (2005). Similarity for ontologies\u2014a comprehensive framework. In Proceedings of the 13th European conference on information systems."},{"key":"9125_CR16","unstructured":"Fissaha Adafre, S., de Rijke, M., & Sang, E. T. K. (2007). Entity retrieval. In Proceedings of international conference on recent advances in natural language processing (RANLP\u20142007), September 27\u201329, Borovets, Bulgaria."},{"key":"9125_CR17","unstructured":"Grivolla, J., Jourlin, P., & de Mori, R. (2005). Automatic classification of queries by expected retrieval performance. In Proceedings of the SIGIR workshop on predicting query difficulty, Salvador, Brazil."},{"key":"9125_CR18","doi-asserted-by":"crossref","unstructured":"Hassell, J., Aleman-Meza, B., & Arpinar, I. B. (2006). Ontology-driven automatic entity disambiguation in unstructured text. In Proceedings of the 5th international semantic web conference (ISWC), Athens, GA, Lecture notes in computer science, Vol. 4273, pp. 44\u201357.","DOI":"10.1007\/11926078_4"},{"issue":"7","key":"9125_CR19","doi-asserted-by":"publisher","first-page":"585","DOI":"10.1016\/j.is.2005.11.003","volume":"31","author":"B. He","year":"2006","unstructured":"He, B., & Ounis, I. (2006). Query performance prediction. Information Systems 31(7), 585\u2013594.","journal-title":"Information Systems"},{"key":"9125_CR20","doi-asserted-by":"crossref","unstructured":"Hu, G., Liu, J., Li, H., Cao, Y., Nie, J. Y., & Gao, J. (2006). A supervised learning approach to entity search. In Proceedings of the Asia information retrieval symposium (AIRS 2006). Lecture notes in computer science, Vol. 4182, pp. 54\u201366.","DOI":"10.1007\/11880592_5"},{"key":"9125_CR21","unstructured":"Kamps, J., & Larsen, B. (2006). Understanding differences between search requests in XML element retrieval. In Proceedings of the SIGIR 2006 workshop on XML element retrieval methodology, Seattle, Washington, pp. 13\u201319."},{"key":"9125_CR22","unstructured":"Kaptein, R., & Kamps, J. (2009). Finding entities or information using annotations. In ECIR workshop on information retrieval over social networks, pp. 71\u201378."},{"key":"9125_CR23","unstructured":"Kazama, J., & Torisawa, K. (2007). Exploiting Wikipedia as external knowledge for named entity recognition. In Proceedings of the 2007 joint conference on EMNLP and CoNLL, Prague, The Czech Republic, pp. 698\u2013707."},{"issue":"5","key":"9125_CR24","doi-asserted-by":"publisher","first-page":"604","DOI":"10.1145\/324133.324140","volume":"46","author":"J. M. Kleinberg","year":"1999","unstructured":"Kleinberg, J. M. (1999). Authoritative sources in hyperlinked environment. Journal of the ACM 46(5), 604\u2013632.","journal-title":"Journal of the ACM"},{"issue":"1\u20132","key":"9125_CR25","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1016\/S0004-3702(99)00100-9","volume":"118","author":"N. Kushmerick","year":"2000","unstructured":"Kushmerick, N. (2000). Wrapper induction: Efficiency and expressiveness. Artificial Intelligence 118(1\u20132), 15\u201368.","journal-title":"Artificial Intelligence"},{"key":"9125_CR26","unstructured":"Kwok, K. (2005). An attempt to identify weakest and strongest queries. In Proceedings of the SIGIR workshop on predicting query difficulty, Salvador, Brazil."},{"issue":"4","key":"9125_CR27","doi-asserted-by":"publisher","first-page":"590","DOI":"10.1007\/s11390-008-9155-6","volume":"23","author":"H. Lang","year":"2008","unstructured":"Lang, H., Wang, B., Jones, G., Li, J. T., Ding, F., & Liu, Y. X. (2008). Query performance prediction for information retrieval based on covering topic score. Journal of Computer Science and technology 23(4), 590\u2013601.","journal-title":"Journal of Computer Science and technology"},{"key":"9125_CR28","doi-asserted-by":"crossref","first-page":"149","DOI":"10.1613\/jair.1145","volume":"18","author":"K. Lerman","year":"2003","unstructured":"Lerman, K., Minton, S. N., & Knoblock, C. A. (2003). Wrapper maintenance: A machine learning approach. Journal of Artificial Intelligence Research 18, 149\u2013181.","journal-title":"Journal of Artificial Intelligence Research"},{"key":"9125_CR29","doi-asserted-by":"crossref","unstructured":"Loper, E., & Bird, S. (2002). NLTK: The natural language toolkit. In Proceedings of the ACL-02 workshop on effective tools and methodologies for teaching natural language processing and computational linguistics, Philadelphia, Pennsylvania, pp. 63\u201370.","DOI":"10.3115\/1118108.1118117"},{"key":"9125_CR30","doi-asserted-by":"crossref","unstructured":"Mizzaro, S. (2008). The good, the bad, the difficult, and the easy: Something wrong with information retrieval evaluation? In Proceedings of the 30th European conference on information retrieval (ECIR\u201908), Lecture Notes in Computer Science, Vol. 4956, pp. 642\u2013646.","DOI":"10.1007\/978-3-540-78646-7_71"},{"key":"9125_CR31","doi-asserted-by":"crossref","unstructured":"Mizzaro, S., & Robertson, S. (2007). HITS hits TREC: Exploring IR evaluation results with network analysis. In Proceedings of the 30th ACM SIGIR conference on research and development in information retrieval (SIGIR\u201907), Amsterdam, The Netherlands, pp. 479\u2013486.","DOI":"10.1145\/1277741.1277824"},{"key":"9125_CR32","unstructured":"Mothe, J., & Tanguy, L. (2005). Linguistic features to predict query difficulty. In Proceedings of the SIGIR workshop on predicting query difficulty, Salvador, Brazil."},{"key":"9125_CR33","doi-asserted-by":"crossref","unstructured":"Nie, L., Davison, B. D., & Qi, X. (2006). Topical link analysis for web search. In Proceedings of the 29th ACM international conference on research and development in information retrieval (SIGIR\u201906), Seattle, Washington, pp. 91\u201398.","DOI":"10.1145\/1148170.1148189"},{"issue":"4","key":"9125_CR34","doi-asserted-by":"publisher","first-page":"571","DOI":"10.1007\/s10791-005-0748-1","volume":"8","author":"J. Pehcevski","year":"2005","unstructured":"Pehcevski, J., Thom, J. A., & Vercoustre, A. M. (2005). Hybrid XML retrieval: Combining information retrieval and a native XML database. Information Retrieval 8(4), 571\u2013600.","journal-title":"Information Retrieval"},{"key":"9125_CR35","doi-asserted-by":"crossref","unstructured":"Pehcevski, J., Vercoustre, A. M., & Thom, J. A. (2008). Exploiting locality of Wikipedia links in entity ranking. In Proceedings of the 30th European conference on information retrieval (ECIR\u201908), Lecture notes in computer science, Vol. 4956, pp. 258\u2013269.","DOI":"10.1007\/978-3-540-78646-7_25"},{"key":"9125_CR36","unstructured":"Quinlan, J. R. (1993). C4.5: Programs for machine learning. Morgan Kaufmann Publishers, Inc."},{"key":"9125_CR37","unstructured":"Sahuguet, A., & Azavant, F. (1999). Building light-weight wrappers for legacy web data-sources using W4F. In Proceedings of 25th international conference on very large data bases (VLDB\u201999), Edinburgh, Scotland, UK, pp. 738\u2013741."},{"key":"9125_CR38","unstructured":"Soboroff, I., de Vries, A. P., & Craswell, N. (2006). Overview of the TREC 2006 Enterprise track. In Proceedings of the fifteenth text retrieval conference (TREC 2006), pp. 32\u201351."},{"key":"9125_CR39","unstructured":"Thom, J. A., Pehcevski, J., & Vercoustre, A. M. (2007). Use of Wikipedia categories in entity ranking. In Proceedings of 12th Australasian document computing symposium (ADCS\u201907), Melbourne, Australia, pp. 56\u201363."},{"key":"9125_CR40","doi-asserted-by":"crossref","unstructured":"Tsikrika, T., Serdyukov, P., Rode, H., Westerveld, T., Aly, R., Hiemstra, D., et al. (2008). Structured document retrieval, multimedia retrieval, and entity ranking using PF\/Tijah. In Focused access to XML documents: Sixth international workshop of the initiative for the evaluation of XML retrieval, INEX 2007, Lecture notes in computer science, Vol. 4862, pp. 306\u2013320.","DOI":"10.1007\/978-3-540-85902-4_27"},{"key":"9125_CR41","doi-asserted-by":"crossref","unstructured":"Vercoustre, A. M., & Paradis, F. (1997). A descriptive language for information object reuse through virtual documents. In 4th International conference on object-oriented information systems (OOIS\u201997), Brisbane, Australia, pp. 299\u2013311.","DOI":"10.1007\/978-1-4471-1525-0_25"},{"key":"9125_CR42","doi-asserted-by":"crossref","unstructured":"Vercoustre, A. M., Pehcevski, J., & Thom, J. A. (2008a). Using Wikipedia categories and links in entity ranking. In Focused access to XML documents: Sixth international workshop of the initiative for the evaluation of XML retrieval, INEX 2007, Lecture notes in computer science, vol. 4862, pp. 321\u2013335.","DOI":"10.1007\/978-3-540-85902-4_28"},{"key":"9125_CR43","doi-asserted-by":"crossref","unstructured":"Vercoustre, A. M., Thom, J. A., & Pehcevski, J. (2008b). Entity ranking in Wikipedia. In Proceedings of the 23rd ACM symposium on applied computing, Fortaleza, Cear\u00e1, Brazil, pp. 1101\u20131106.","DOI":"10.1145\/1363686.1363943"},{"key":"9125_CR44","doi-asserted-by":"crossref","unstructured":"Vercoustre, A. M., Pehcevski, J., & Naumovski, V. (2009). Topic difficulty prediction in entity ranking. In Advances in focused retrieval: Seventh international workshop of the initiative for the evaluation of XML retrieval, INEX 2008, Lecture notes in computer science, Vol. 5631.","DOI":"10.1007\/978-3-642-03761-0_29"},{"key":"9125_CR45","doi-asserted-by":"crossref","unstructured":"Voorhees, E. M. (2004). The TREC robust retrieval track. In Proceedings of the thirteenth text retrieval conference (TREC 2004).","DOI":"10.6028\/NIST.SP.500-261"},{"key":"9125_CR47","doi-asserted-by":"crossref","unstructured":"Webber, W., Moffat, A., & Zobel, J. (2008). Score standardization for inter-collection comparison of retrieval systems. In Proceedings of the 31st ACM SIGIR conference on research and development in information retrieval (SIGIR\u201908), Singapore, pp. 51\u201358.","DOI":"10.1145\/1390334.1390346"},{"key":"9125_CR48","unstructured":"Witten, I. H., & Frank, E. (2005). Data mining: Practical machine learning tools and techniques, second edition. Morgan Kaufmann Publishers, Inc."},{"key":"9125_CR49","doi-asserted-by":"crossref","unstructured":"Yom-Tov, E., Fine, S., Carmel, D., Darlow, A., & Amitay, E. (2004). Juru at TREC 2004: Experiments with prediction of query difficulty. In Proceedings of the thirteenth text retrieval conference (TREC 2004).","DOI":"10.6028\/NIST.SP.500-261.robust-ibm.haifa.carmel"},{"key":"9125_CR50","doi-asserted-by":"crossref","unstructured":"Yu, J., Thom, J. A., & Tam, A. (2007). Ontology evaluation using Wikipedia categories for browsing. In Proceedings of the 16th ACM conference on information and knowledge management (CIKM\u201907), Lisboa, Portugal, pp. 223\u2013232.","DOI":"10.1145\/1321440.1321474"},{"key":"9125_CR51","doi-asserted-by":"crossref","unstructured":"Zhou, Y., & Croft, W. B. (2007). Query performance prediction in web search environments. In Proceedings of the 30th ACM SIGIR conference on research and development in information retrieval (SIGIR\u201907), Amsterdam, The Netherlands, pp. 543\u2013550.","DOI":"10.1145\/1277741.1277835"}],"container-title":["Information Retrieval"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10791-009-9125-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10791-009-9125-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10791-009-9125-9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10791-009-9125-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,16]],"date-time":"2025-02-16T15:50:34Z","timestamp":1739721034000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10791-009-9125-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010,1,9]]},"references-count":51,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2010,10]]}},"alternative-id":["9125"],"URL":"https:\/\/doi.org\/10.1007\/s10791-009-9125-9","relation":{},"ISSN":["1386-4564","1573-7659"],"issn-type":[{"type":"print","value":"1386-4564"},{"type":"electronic","value":"1573-7659"}],"subject":[],"published":{"date-parts":[[2010,1,9]]},"assertion":[{"value":"8 May 2009","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 December 2009","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 January 2010","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}