{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T06:17:56Z","timestamp":1775283476392,"version":"3.50.1"},"publisher-location":"Berlin, Heidelberg","reference-count":23,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"value":"9783540329602","type":"print"},{"value":"9783540329619","type":"electronic"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2006]]},"DOI":"10.1007\/11687238_21","type":"book-chapter","created":{"date-parts":[[2006,3,9]],"date-time":"2006-03-09T07:05:50Z","timestamp":1141887950000},"page":"313-330","source":"Crossref","is-referenced-by-count":27,"title":["Indexing Shared Content in Information Retrieval Systems"],"prefix":"10.1007","author":[{"given":"Andrei Z.","family":"Broder","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nadav","family":"Eiron","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marcus","family":"Fontoura","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael","family":"Herscovici","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ronny","family":"Lempel","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"John","family":"McPherson","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Runping","family":"Qi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eugene","family":"Shekita","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"21_CR1","volume-title":"Modern Information Retrieval","author":"R. Baeza-Yates","year":"1999","unstructured":"Baeza-Yates, R., Ribeiro-Neto, B.: Modern Information Retrieval. Addison Wesley, Reading (1999)"},{"key":"21_CR2","doi-asserted-by":"crossref","unstructured":"Bilenko, M., Mooney, R.J.: Adaptive duplicate detection using learnable string similarity measures. In: KDD 2003, pp. 39\u201348 (2003)","DOI":"10.1145\/956750.956759"},{"key":"21_CR3","doi-asserted-by":"crossref","unstructured":"Brin, S., Page, L.: The anatomy of a large-scale hypertextual Web search engine. In: WWW 1998, pp. 107\u2013117 (1998)","DOI":"10.1016\/S0169-7552(98)00110-X"},{"key":"21_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/3-540-45123-4_1","volume-title":"Combinatorial Pattern Matching","author":"A. Broder","year":"2000","unstructured":"Broder, A.: Identifying and filtering near-duplicate documents. In: Giancarlo, R., Sankoff, D. (eds.) CPM 2000. LNCS, vol.\u00a01848, pp. 1\u201310. Springer, Heidelberg (2000)"},{"key":"21_CR5","doi-asserted-by":"crossref","unstructured":"Broder, A.Z., Carmel, D., Herscovici, M., Soffer, A., Zien, J.: Efficient query evaluation using a two-level retrieval process. In: CIKM 2003, pp. 426\u2013434 (2003)","DOI":"10.1145\/956863.956944"},{"key":"21_CR6","doi-asserted-by":"crossref","unstructured":"Broder, A.Z., Glassman, S.C., Manasse, M.S., Zweig, G.: Syntactic clustering of the web. In: WWW 1997, pp. 1157\u20131166 (1997)","DOI":"10.1016\/S0169-7552(97)00031-7"},{"key":"21_CR7","doi-asserted-by":"crossref","unstructured":"Carmel, D., Cohen, D., Fagin, R., Farchi, E., Herscovici, M., Maarek, Y.S., Soffer, A.: Static index pruning for information retrieval systems. In: SIGIR 2001, pp. 43\u201350 (2001)","DOI":"10.1145\/383952.383958"},{"key":"21_CR8","doi-asserted-by":"crossref","unstructured":"Cho, J., Shivakumar, N., Garcia-Molina, H.: Finding replicated web collections. In: SIGMOD 2000, pp. 355\u2013366 (2000)","DOI":"10.1145\/342009.335429"},{"key":"21_CR9","doi-asserted-by":"crossref","unstructured":"de Moura, E.S., dos Santos, C.F., Fernandes, D.R., Silva, A.S., Calado, P., Nascimento, M.A.: Improving web search efficiency via a locality based static pruning method. In: WWW 2005, pp. 235\u2013244 (2005)","DOI":"10.1145\/1060745.1060783"},{"key":"21_CR10","doi-asserted-by":"crossref","unstructured":"Fontoura, M., Shekita, E.J., Zien, J.Y., Rajagopalan, S., Neumann, A.: High performance index build algorithms for intranet search engines. In: VLDB 2004, pp. 1158\u20131169 (2004)","DOI":"10.1016\/B978-012088469-8.50101-7"},{"key":"21_CR11","volume-title":"Database System Implementation","author":"H. Garcia-Molina","year":"2000","unstructured":"Garcia-Molina, H., Ullman, J., Widom, J.: Database System Implementation. Prentice Hall, Englewood Cliffs (2000)"},{"key":"21_CR12","unstructured":"Gmail, http:\/\/gmail.google.com\/gmail\/help\/about.html"},{"key":"21_CR13","doi-asserted-by":"crossref","unstructured":"Heinz, S., Zobel, J.: Efficient single-pass index construction for text databases. JASIST\u00a054(8) (2003)","DOI":"10.1002\/asi.10268"},{"key":"21_CR14","series-title":"Lecture Notes in Artificial Intelligence","doi-asserted-by":"publisher","first-page":"217","DOI":"10.1007\/978-3-540-30115-8_22","volume-title":"Machine Learning: ECML 2004","author":"B. Klimt","year":"2004","unstructured":"Klimt, B., Yang, Y.: The Enron corpus: A new dataset for email classification research. In: Boulicaut, J.-F., Esposito, F., Giannotti, F., Pedreschi, D. (eds.) ECML 2004. LNCS (LNAI), vol.\u00a03201, pp. 217\u2013226. Springer, Heidelberg (2004)"},{"key":"21_CR15","doi-asserted-by":"crossref","unstructured":"Long, X., Suel, T.: Optimized query execution in large search engines with global page ordering. In: VLDB 2003, pp. 129\u2013140 (2003)","DOI":"10.1016\/B978-012722442-8\/50020-3"},{"key":"21_CR16","doi-asserted-by":"crossref","unstructured":"Melnik, S., Raghavan, S., Yang, B., Garcia-Molina, H.: Building a distributed full-text index for the web. In: WWW 2001, pp. 396\u2013406 (2001)","DOI":"10.1145\/371920.372095"},{"key":"21_CR17","unstructured":"Moffat, A., Zobel, J.: Compression and fast indexing for multi-gigabyte text databases. Australian Computer Journal\u00a026(1) (1994)"},{"key":"21_CR18","doi-asserted-by":"crossref","unstructured":"Scholer, F., Williams, H.E., Yiannis, J., Zobel, J.: Compression of inverted indexes for fast query evaluation. In: SIGIR 2002, pp. 222\u2013229 (2002)","DOI":"10.1145\/564376.564416"},{"key":"21_CR19","doi-asserted-by":"crossref","unstructured":"Stata, R., Hunt, P., Thiruvalluvan, M.G.: The Bloomba personal content database. In: VLDB 2004, pp. 1214\u20131223 (2004)","DOI":"10.1016\/B978-012088469-8.50108-X"},{"issue":"6","key":"21_CR20","doi-asserted-by":"publisher","first-page":"831","DOI":"10.1016\/0306-4573(95)00020-H","volume":"31","author":"H. Turtle","year":"1995","unstructured":"Turtle, H., Flood, J.: Query evaluation: strategies and optimizations. Inf. Proc. Management\u00a031(6), 831\u2013850 (1995)","journal-title":"Inf. Proc. Management"},{"key":"21_CR21","volume-title":"Managing Gigabytes","author":"I. Witten","year":"1999","unstructured":"Witten, I., Moffat, A., Bell, T.: Managing Gigabytes. Morgan Kaufmann, San Francisco (1999)"},{"key":"21_CR22","unstructured":"Zhang, Z.: The behavior of duplicate pages on the world wide web. Submitted to CIKM (2005)"},{"key":"21_CR23","doi-asserted-by":"crossref","unstructured":"Zobel, J., Moffat, A.: Adding compression to a full-text retrieval system. Software - Practice & Experience\u00a025(8) (1995)","DOI":"10.1002\/spe.4380250804"}],"container-title":["Lecture Notes in Computer Science","Advances in Database Technology - EDBT 2006"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/11687238_21.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,4,27]],"date-time":"2021-04-27T07:17:12Z","timestamp":1619507832000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/11687238_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2006]]},"ISBN":["9783540329602","9783540329619"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/11687238_21","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2006]]}}}