{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T06:07:10Z","timestamp":1775282830449,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":39,"publisher":"ACM","license":[{"start":{"date-parts":[[2009,2,9]],"date-time":"2009-02-09T00:00:00Z","timestamp":1234137600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2009,2,9]]},"DOI":"10.1145\/1498759.1498806","type":"proceedings-article","created":{"date-parts":[[2009,2,10]],"date-time":"2009-02-10T16:46:07Z","timestamp":1234284367000},"page":"34-43","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":62,"title":["Query by document"],"prefix":"10.1145","author":[{"given":"Yin","family":"Yang","sequence":"first","affiliation":[{"name":"Computer Science, HKUST"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nilesh","family":"Bansal","sequence":"additional","affiliation":[{"name":"University of Toronto"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wisam","family":"Dakka","sequence":"additional","affiliation":[{"name":"Search Quality, Google Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Panagiotis","family":"Ipeirotis","sequence":"additional","affiliation":[{"name":"New York University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nick","family":"Koudas","sequence":"additional","affiliation":[{"name":"University of Toronto"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dimitris","family":"Papadias","sequence":"additional","affiliation":[{"name":"Computer Science, HKUST"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2009,2,9]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/133160.133169"},{"key":"e_1_3_2_1_2_1","volume-title":"VLDB","author":"Bansal N.","year":"2007","unstructured":"Bansal , N. , Chiang , F. , Koudas , N. , Tompa , F. W. Seeking Stable Clusters in the Blogosphere . In VLDB , 2007 . Bansal, N., Chiang, F., Koudas, N., Tompa, F. W. Seeking Stable Clusters in the Blogosphere. In VLDB, 2007."},{"key":"e_1_3_2_1_3_1","volume-title":"BlogScope: A System for Online Analysis of High","author":"Bansal N.","unstructured":"Bansal , N. , Koudas , N. BlogScope: A System for Online Analysis of High Volume Text Streams In VLDB, 2007 . Bansal, N., Koudas, N. BlogScope: A System for Online Analysis of High Volume Text Streams In VLDB, 2007."},{"key":"e_1_3_2_1_4_1","unstructured":"BlogScope http:\/\/www.blogscope.net\/about\/  BlogScope http:\/\/www.blogscope.net\/about\/"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.3115\/981623.981633"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/1247480.1247521"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1006569829653"},{"key":"e_1_3_2_1_8_1","volume-title":"EMNLP-CoNLL","author":"Cucerzan S.","year":"2007","unstructured":"Cucerzan , S. Large-Scale Named Entity Disambiguation Based on Wikipedia Data . In EMNLP-CoNLL , 2007 . Cucerzan, S. Large-Scale Named Entity Disambiguation Based on Wikipedia Data. In EMNLP-CoNLL, 2007."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.3115\/974358.974367"},{"key":"e_1_3_2_1_10_1","first-page":"121","volume":"31","author":"Efthmiadis","year":"1996","unstructured":"Efthmiadis , E. Query Expansion. In Annual Review of Information Science and Technology , 31 : 121 -- 187 , 1996 . Efthmiadis, E. Query Expansion. In Annual Review of Information Science and Technology, 31:121--187, 1996.","journal-title":"Query Expansion. In Annual Review of Information Science and Technology"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/1242572.1242667"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/42005.42016"},{"key":"e_1_3_2_1_13_1","volume-title":"An Introduction to Probability Theory and Its Applications","author":"Feller W.","year":"1968","unstructured":"Feller , W. An Introduction to Probability Theory and Its Applications , Wiley , 1968 . Feller, W. An Introduction to Probability Theory and Its Applications, Wiley, 1968."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.3115\/976909.979682"},{"key":"e_1_3_2_1_15_1","volume-title":"WWW","author":"Gravano L.","year":"2003","unstructured":"Gravano , L. , Ipeirotis , P. , Koudas , N. , Srivastava , D. Text Joins for Data Cleasing and Integration in an RDBMS . In WWW , 2003 . Gravano, L., Ipeirotis, P., Koudas, N., Srivastava, D. Text Joins for Data Cleasing and Integration in an RDBMS. In WWW, 2003."},{"key":"e_1_3_2_1_16_1","volume-title":"VLDB","author":"Gyongyi Z.","year":"2004","unstructured":"Gyongyi , Z. , Garcia-Molina , H. , Petersen , J. Combating Web Spam with TrustRank . In VLDB , 2004 . Gyongyi, Z., Garcia-Molina, H., Petersen, J. Combating Web Spam with TrustRank. In VLDB, 2004."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/133160.133167"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/511446.511513"},{"key":"e_1_3_2_1_19_1","volume-title":"The SMART Retrieval System - Experiments in Automatic Document Processing","author":"Ide E.","year":"1971","unstructured":"Ide , E. New Experiments in Relevance Feedback . In The SMART Retrieval System - Experiments in Automatic Document Processing , Prentice-Hall , 1971 . Ide, E. New Experiments in Relevance Feedback. In The SMART Retrieval System - Experiments in Automatic Document Processing, Prentice-Hall, 1971."},{"key":"e_1_3_2_1_20_1","volume-title":"Soviet Physics Doklady","author":"Levenshtein V.","year":"1966","unstructured":"Levenshtein , V. Binary codes capable of correcting deletions, insertions, and reversals . In Soviet Physics Doklady 1966 . Levenshtein, V. Binary codes capable of correcting deletions, insertions, and reversals. In Soviet Physics Doklady 1966."},{"key":"e_1_3_2_1_21_1","volume-title":"TREC","author":"MacDonald C.","year":"2005","unstructured":"MacDonald , C. , He , B. , Plachouras , V. , Ounis , I. University of Glasgow at TREC 2005: Experiments in Terabyte and Enterprise Tracks with Terrier . In TREC , 2005 . MacDonald, C., He, B., Plachouras, V., Ounis, I. University of Glasgow at TREC 2005: Experiments in Terabyte and Enterprise Tracks with Terrier. In TREC, 2005."},{"key":"e_1_3_2_1_22_1","volume-title":"Foundations and Statistical Natural Language Processing","author":"Manning C.","year":"1989","unstructured":"Manning , C. , Schutze , H. Foundations and Statistical Natural Language Processing , MIT Press , 1989 . Manning, C., Schutze, H. Foundations and Statistical Natural Language Processing, MIT Press, 1989."},{"key":"e_1_3_2_1_23_1","volume-title":"O. Computing Lexical Chains with Graph Clustering In ACL","author":"Medelyan","year":"2007","unstructured":"Medelyan , O. Computing Lexical Chains with Graph Clustering In ACL 2007 . Medelyan, O. Computing Lexical Chains with Graph Clustering In ACL 2007."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/1141753.1141819"},{"key":"e_1_3_2_1_25_1","volume-title":"C. An Analysis of Statistical and Sytactic Phrases. In RIAO Conference","author":"Mitra M.","year":"1997","unstructured":"Mitra , M. , Buckley , C. , Singhal , A. , Cardie , C. An Analysis of Statistical and Sytactic Phrases. In RIAO Conference , 1997 . Mitra, M., Buckley, C., Singhal, A., Cardie, C. An Analysis of Statistical and Sytactic Phrases. In RIAO Conference, 1997."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1026520926673"},{"key":"e_1_3_2_1_27_1","unstructured":"Amazon Mechanical Turk. http:\/\/www.mturk.com  Amazon Mechanical Turk. http:\/\/www.mturk.com"},{"key":"e_1_3_2_1_28_1","volume-title":"A statistical corpus based term extractor Lecture notes in AI","author":"Pantel P.","year":"2001","unstructured":"Pantel , P. , Lin , D. A statistical corpus based term extractor Lecture notes in AI , 2001 , Springer-Verlag Pantel, P., Lin, D. A statistical corpus based term extractor Lecture notes in AI, 2001, Springer-Verlag"},{"key":"e_1_3_2_1_29_1","unstructured":"Part-of-speech tagging. http:\/\/en.wikipedia.org\/wiki\/Part-of-speech_tagging  Part-of-speech tagging. http:\/\/en.wikipedia.org\/wiki\/Part-of-speech_tagging"},{"key":"e_1_3_2_1_30_1","volume-title":"The SMART Retrieval System - Experiments in Automatic Document Processing","author":"Rocchio J.","year":"1971","unstructured":"Rocchio , J. Relevance Feedback in Information Retrieval . In The SMART Retrieval System - Experiments in Automatic Document Processing , Prentice-Hall , 1971 . Rocchio, J. Relevance Feedback in Information Retrieval. In The SMART Retrieval System - Experiments in Automatic Document Processing, Prentice-Hall, 1971."},{"key":"e_1_3_2_1_31_1","volume-title":"Introduction to modern information retrieval","author":"Salton G.","year":"1983","unstructured":"Salton , G. and McGill , M. J. Introduction to modern information retrieval . McGraw-Hill , 1983 . Salton, G. and McGill, M. J. Introduction to modern information retrieval. McGraw-Hill, 1983."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1108\/10662240010342621"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.3115\/1119282.1119287"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1009976227802"},{"key":"e_1_3_2_1_35_1","volume-title":"TREC","author":"Vechtomova O.","year":"2004","unstructured":"Vechtomova , O. , Karamuftuoglu , M. Approaches to High Accuracy Retrieval: Phrase-Based Search Experiments in the HARD Track . In TREC , 2004 . Vechtomova, O., Karamuftuoglu, M. Approaches to High Accuracy Retrieval: Phrase-Based Search Experiments in the HARD Track. In TREC, 2004."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/313238.313437"},{"key":"e_1_3_2_1_37_1","unstructured":"Yahoo Term Extraction Web Service. http:\/\/developer.yahoo.com\/search\/content\/V1\/termExtraction.html  Yahoo Term Extraction Web Service. http:\/\/developer.yahoo.com\/search\/content\/V1\/termExtraction.html"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/1321440.1321599"},{"key":"e_1_3_2_1_39_1","volume-title":"Datamonitor","author":"The Future","year":"2007","unstructured":"The Future of Social Networking : Understanding Market Stratigic and Technology developments . Datamonitor , 2007 . The Future of Social Networking: Understanding Market Stratigic and Technology developments. Datamonitor, 2007."}],"event":{"name":"WSDM'09: Second ACM International Conference on Web Search and Web Data Mining","location":"Barcelona Spain","acronym":"WSDM'09","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","Yahoo! Research","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data","Nokia","Google Inc.","SIGIR ACM Special Interest Group on Information Retrieval","Microsoft Microsoft"]},"container-title":["Proceedings of the Second ACM International Conference on Web Search and Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1498759.1498806","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/1498759.1498806","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T13:38:38Z","timestamp":1750253918000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1498759.1498806"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2009,2,9]]},"references-count":39,"alternative-id":["10.1145\/1498759.1498806","10.1145\/1498759"],"URL":"https:\/\/doi.org\/10.1145\/1498759.1498806","relation":{},"subject":[],"published":{"date-parts":[[2009,2,9]]},"assertion":[{"value":"2009-02-09","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}