{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,5]],"date-time":"2025-10-05T16:59:27Z","timestamp":1759683567663,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":43,"publisher":"ACM","license":[{"start":{"date-parts":[[2006,6,27]],"date-time":"2006-06-27T00:00:00Z","timestamp":1151366400000},"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":[[2006,6,27]]},"DOI":"10.1145\/1142473.1142504","type":"proceedings-article","created":{"date-parts":[[2006,7,24]],"date-time":"2006-07-24T16:53:01Z","timestamp":1153759981000},"page":"265-276","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":42,"title":["To search or to crawl?"],"prefix":"10.1145","author":[{"given":"Panagiotis G.","family":"Ipeirotis","sequence":"first","affiliation":[{"name":"New York University"}]},{"given":"Eugene","family":"Agichtein","sequence":"additional","affiliation":[{"name":"Microsoft Research"}]},{"given":"Pranay","family":"Jain","sequence":"additional","affiliation":[{"name":"Columbia University"}]},{"given":"Luis","family":"Gravano","sequence":"additional","affiliation":[{"name":"Columbia University"}]}],"member":"320","published-online":{"date-parts":[[2006,6,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/336597.336644"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2003.1260786"},{"key":"e_1_3_2_1_3_1","volume-title":"WebDB","author":"Agichtein E.","year":"2003","unstructured":"E. Agichtein , P. G. Ipeirotis , and L. Gravano . Modeling query-based access to text databases . In WebDB , 2003 .]] E. Agichtein, P. G. Ipeirotis, and L. Gravano. Modeling query-based access to text databases. In WebDB, 2003.]]"},{"key":"e_1_3_2_1_4_1","volume-title":"Symp. on Mining Answers from Texts and KBases","author":"Banko M.","year":"2002","unstructured":"M. Banko , E. Brill , S. Dumais , and J. Lin . AskMSR: Question answering using the World-Wide Web . In Symp. on Mining Answers from Texts and KBases , 2002 .]] M. Banko, E. Brill, S. Dumais, and J. Lin. AskMSR: Question answering using the World-Wide Web. In Symp. on Mining Answers from Texts and KBases, 2002.]]"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.3998\/3336451.0007.104"},{"key":"e_1_3_2_1_6_1","unstructured":"C. L. Blake and C. J. Merz. UCI repository of machine learning databases. http:\/\/www.ics.uci.edu\/\u00bfmlearn\/MLRepository.html]]  C. L. Blake and C. J. Merz. UCI repository of machine learning databases. http:\/\/www.ics.uci.edu\/\u00bfmlearn\/MLRepository.html]]"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.5555\/646543.696220"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/1060745.1060811"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/382979.383040"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/304182.304224"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/215206.215328"},{"key":"e_1_3_2_1_12_1","volume-title":"Morgan Kaufmann","author":"Chakrabarti S.","year":"2002","unstructured":"S. Chakrabarti . Mining the Web . Morgan Kaufmann , 2002 .]] S. Chakrabarti. Mining the Web. Morgan Kaufmann, 2002.]]"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/511446.511466"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/S1389-1286(99)00052-3"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/872757.872796"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/276304.276343"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/320248.320249"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1007\/PL00012580"},{"key":"e_1_3_2_1_19_1","volume-title":"AAAI","author":"Cohen W. W.","year":"1996","unstructured":"W. W. Cohen . Learning trees and rules with set-valued features . In AAAI , 1996 .]] W. W. Cohen. Learning trees and rules with set-valued features. In AAAI, 1996.]]"},{"key":"e_1_3_2_1_20_1","volume-title":"AAAI Workshop on Internet-Based Information Systems","author":"Cohen W. W.","year":"1996","unstructured":"W. W. Cohen and Y. Singer . Learning to query the web . In AAAI Workshop on Internet-Based Information Systems , 1996 .]] W. W. Cohen and Y. Singer. Learning to query the web. In AAAI Workshop on Internet-Based Information Systems, 1996.]]"},{"key":"e_1_3_2_1_21_1","volume-title":"VLDB","author":"Diligenti M.","year":"2000","unstructured":"M. Diligenti , F. Coetzee , S. Lawrence , C. L. Giles , and M. Gori . Focused crawling using context graphs . In VLDB , 2000 .]] M. Diligenti, F. Coetzee, S. Lawrence, C. L. Giles, and M. Gori. Focused crawling using context graphs. In VLDB, 2000.]]"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/267658.267666"},{"key":"e_1_3_2_1_23_1","volume-title":"Pattern Classification and Scene Analysis","author":"Duda R. O.","year":"1973","unstructured":"R. O. Duda and P. E. Hart . Pattern Classification and Scene Analysis . Wiley , 1973 .]] R. O. Duda and P. E. Hart. Pattern Classification and Scene Analysis. Wiley, 1973.]]"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/988672.988687"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/320248.320252"},{"key":"e_1_3_2_1_26_1","volume-title":"Query- vs. crawling-based classification of searchable web databases","author":"Gravano L.","year":"2002","unstructured":"L. Gravano , P. G. Ipeirotis , and M. Sahami . Query- vs. crawling-based classification of searchable web databases . IEEE Data Eng. Bull ., 25(1), 2002 .]] L. Gravano, P. G. Ipeirotis, and M. Sahami. Query- vs. crawling-based classification of searchable web databases. IEEE Data Eng. Bull., 25(1), 2002.]]"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/635484.635485"},{"key":"e_1_3_2_1_28_1","volume-title":"SCIE","author":"Grishman R.","year":"1997","unstructured":"R. Grishman . Information extraction : Techniques and challenges . In SCIE , 1997 .]] R. Grishman. Information extraction: Techniques and challenges. In SCIE, 1997.]]"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1016\/S1532-0464(03)00013-3"},{"key":"e_1_3_2_1_30_1","volume-title":"thesis","author":"Ipeirotis P. G.","year":"2004","unstructured":"P. G. Ipeirotis . Classifying and Searching Hidden-Web Text Databases. Ph. D. thesis , Columbia University , 2004 .]] P. G. Ipeirotis. Classifying and Searching Hidden-Web Text Databases. Ph.D. thesis, Columbia University, 2004.]]"},{"key":"e_1_3_2_1_31_1","volume-title":"VLDB","author":"Ipeirotis P. G.","year":"2002","unstructured":"P. G. Ipeirotis and L. Gravano . Distributed search over the hidden web: Hierarchical database sampling and selection . In VLDB , 2002 .]] P. G. Ipeirotis and L. Gravano. Distributed search over the hidden web: Hierarchical database sampling and selection. In VLDB, 2002.]]"},{"key":"e_1_3_2_1_32_1","volume-title":"ICDE","author":"Ling Y.","year":"1995","unstructured":"Y. Ling and W. Sun . An evaluation of sampling-based size estimation methods for selections in database systems . In ICDE , 1995 .]] Y. Ling and W. Sun. An evaluation of sampling-based size estimation methods for selections in database systems. In ICDE, 1995.]]"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/1031114.1031117"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1080\/15427951.2004.10129092"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.64.026118"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/1065385.1065407"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1008287121180"},{"key":"e_1_3_2_1_38_1","volume-title":"Introduction to Probability Models","author":"Ross S. M.","year":"2002","unstructured":"S. M. Ross . Introduction to Probability Models . Academic Press , 8 th ed., 2002 .]] S. M. Ross. Introduction to Probability Models. Academic Press, 8th ed., 2002.]]","edition":"8"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/505282.505283"},{"key":"e_1_3_2_1_40_1","volume-title":"Statistical Learning Theory","author":"Vapnik V. N.","year":"1998","unstructured":"V. N. Vapnik . Statistical Learning Theory . Wiley-Interscience , Sept. 1998 .]] V. N. Vapnik. Statistical Learning Theory. Wiley-Interscience, Sept. 1998.]]"},{"key":"e_1_3_2_1_41_1","volume-title":"Academic Press Professional","author":"Wilf H. S.","year":"1990","unstructured":"H. S. Wilf . Generatingfunctionology. Academic Press Professional , Inc ., 1990 .]] H. S. Wilf. Generatingfunctionology. Academic Press Professional, Inc., 1990.]]"},{"key":"e_1_3_2_1_42_1","volume-title":"MUC-7","author":"Yangarber R.","year":"1998","unstructured":"R. Yangarber and R. Grishman . NYU: Description of the Proteus\/PET system as used for MUC-7 . In MUC-7 , 1998 .]] R. Yangarber and R. Grishman. NYU: Description of the Proteus\/PET system as used for MUC-7. In MUC-7, 1998.]]"},{"key":"e_1_3_2_1_43_1","volume-title":"Human Behavior and the Principle of Least Effort","author":"Zipf G. K.","year":"1949","unstructured":"G. K. Zipf . Human Behavior and the Principle of Least Effort . 1949 .]] G. K. Zipf. Human Behavior and the Principle of Least Effort. 1949.]]"}],"event":{"name":"SIGMOD\/PODS06: International Conference on Management of Data and Symposium on Principles Database and Systems","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","ACM Association for Computing Machinery"],"location":"Chicago IL USA","acronym":"SIGMOD\/PODS06"},"container-title":["Proceedings of the 2006 ACM SIGMOD international conference on Management of data"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1142473.1142504","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/1142473.1142504","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T15:06:19Z","timestamp":1750259179000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1142473.1142504"}},"subtitle":["towards a query optimizer for text-centric tasks"],"short-title":[],"issued":{"date-parts":[[2006,6,27]]},"references-count":43,"alternative-id":["10.1145\/1142473.1142504","10.1145\/1142473"],"URL":"https:\/\/doi.org\/10.1145\/1142473.1142504","relation":{},"subject":[],"published":{"date-parts":[[2006,6,27]]},"assertion":[{"value":"2006-06-27","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}