{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,16]],"date-time":"2026-10-16T18:04:02Z","timestamp":1792173842999,"version":"4.4.0"},"reference-count":22,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2011,4]]},"DOI":"10.1109\/icde.2011.5767931","type":"proceedings-article","created":{"date-parts":[[2011,5,17]],"date-time":"2011-05-17T20:45:21Z","timestamp":1305665121000},"page":"685-696","source":"Crossref","is-referenced-by-count":5,"title":["Selectivity estimation for extraction operators over text data"],"prefix":"10.1109","author":[{"given":"Daisy Zhe","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Long","family":"Wei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yunyao","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Frederick","family":"Reiss","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shivakumar","family":"Vaithyanathan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Estimating the selectivity of xml path expressions for internet scale applications","author":"aboulnaga","year":"0","journal-title":"Proceedings of the Very Large Databases Conference"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/B978-012088469-8.50024-3"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511809071.013"},{"key":"ref13","author":"jurafsky","year":"2009","journal-title":"Speech and Language Processing"},{"key":"ref14","article-title":"Enron Dataset","year":"0"},{"key":"ref15","article-title":"Declarative information extraction using datalog with embedded extraction predicates","author":"shen","year":"0","journal-title":"Proceedings of the Very Large Databases Conference"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/872785.872787"},{"key":"ref17","article-title":"An improved data stream summary: The count-min sketch and its applications","author":"commode","year":"2004","journal-title":"J Algorithms"},{"key":"ref18","first-page":"468","article-title":"Smoothed bloom filter language models: Tera-scalc lms on the cheap","author":"talbot","year":"2007","journal-title":"EMNLP"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/362686.362692"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/582095.582099"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/234313.234367"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s007780000029"},{"key":"ref5","article-title":"Selectivity estimation for string predicates: Overcoming the underestimation problem","author":"chaudhuri","year":"2004"},{"key":"ref8","article-title":"Extending q-grams to estimate selectivity of string matching with low edit distance","author":"lee","year":"0","journal-title":"Proceedings of the Very Large Databases Conference"},{"key":"ref7","article-title":"Estimating alphanumeric selectivity in the presence of wildcards","author":"krishnan","year":"0","journal-title":"Proceedings of the ACM SIGMOD Conference"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/275487.275492"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2008.4497502"},{"key":"ref9","article-title":"Selectivity estimation for fuzzy string predicates in large data sets","author":"li","year":"0","journal-title":"Proceedings of the Very Large Databases Conference"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/285243.285287"},{"key":"ref22","first-page":"1002","article-title":"Domain adaptation of rule-based annotators for named-entity recognition tasks","author":"chiticariu","year":"2010","journal-title":"EMNLP"},{"key":"ref21","author":"habibi","year":"2003","journal-title":"Java Regular Expressions Taming the java util regex Engine"}],"event":{"name":"2011 IEEE International Conference on Data Engineering (ICDE 2011)","location":"Hannover, Germany","start":{"date-parts":[[2011,4,11]]},"end":{"date-parts":[[2011,4,16]]}},"container-title":["2011 IEEE 27th International Conference on Data Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/5765035\/5767827\/05767931.pdf?arnumber=5767931","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,3,21]],"date-time":"2017-03-21T07:38:18Z","timestamp":1490081898000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/5767931\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011,4]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icde.2011.5767931","relation":{},"subject":[],"published":{"date-parts":[[2011,4]]}}}