{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T04:31:58Z","timestamp":1750307518235,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":31,"publisher":"ACM","license":[{"start":{"date-parts":[[2009,6,29]],"date-time":"2009-06-29T00:00:00Z","timestamp":1246233600000},"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":[[2009,6,29]]},"DOI":"10.1145\/1559845.1559881","type":"proceedings-article","created":{"date-parts":[[2009,7,8]],"date-time":"2009-07-08T17:34:19Z","timestamp":1247074459000},"page":"321-334","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["Optimizing complex extraction programs over evolving text data"],"prefix":"10.1145","author":[{"given":"Fei","family":"Chen","sequence":"first","affiliation":[{"name":"University of Wisconsin-Madison, Madison, WI, USA"}]},{"given":"Byron J.","family":"Gao","sequence":"additional","affiliation":[{"name":"Texas State University-San Marcos, San Marcos, TX, USA"}]},{"given":"AnHai","family":"Doan","sequence":"additional","affiliation":[{"name":"University of Wisconsin-Madison, Madison, WI, USA"}]},{"given":"Jun","family":"Yang","sequence":"additional","affiliation":[{"name":"Duke University, Durham, NC, USA"}]},{"given":"Raghu","family":"Ramakrishnan","sequence":"additional","affiliation":[{"name":"Yahoo! Research, Santa Clara, CA, USA"}]}],"member":"320","published-online":{"date-parts":[[2009,6,29]]},"reference":[{"unstructured":"http:\/\/langrid.nict.go.jp.  http:\/\/langrid.nict.go.jp.","key":"e_1_3_2_1_1_1"},{"unstructured":"E. Agichtein and S. Sarawagi. Scalable information extraction and integration (tutorial). KDD-06.  E. Agichtein and S. Sarawagi. Scalable information extraction and integration (tutorial). KDD-06.","key":"e_1_3_2_1_2_1"},{"issue":"1","key":"e_1_3_2_1_3_1","first-page":"28","article-title":"Towards a scalable enterprise content analytics platform","volume":"32","author":"Beyer K.","year":"2009","unstructured":"K. Beyer , V. Ercegovac , R. Krishnamurthy , S. Raghavan , J. Rao , F. Reiss , E. J. Shekita , D. Simmen , S. Tata , S. Vaithyanathan , and H. Zhu . Towards a scalable enterprise content analytics platform . IEEE Data Eng. Bull. , 32 ( 1 ): 28 -- 35 , 2009 . K. Beyer, V. Ercegovac, R. Krishnamurthy, S. Raghavan, J. Rao, F. Reiss, E. J. Shekita, D. Simmen, S. Tata, S. Vaithyanathan, and H. Zhu. Towards a scalable enterprise content analytics platform. IEEE Data Eng. Bull., 32(1):28--35, 2009.","journal-title":"IEEE Data Eng. Bull."},{"unstructured":"B. Bhattacharjee V. Ercegovac J. Glider R. Golding G. Lohman V. Markl H. Pirahesh J. Rao R. Rees F. Reiss E. Shekita and G. Swart. Impliance: A next generation information management appliance. CIDR-07.  B. Bhattacharjee V. Ercegovac J. Glider R. Golding G. Lohman V. Markl H. Pirahesh J. Rao R. Rees F. Reiss E. Shekita and G. Swart. Impliance: A next generation information management appliance. CIDR-07.","key":"e_1_3_2_1_4_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_5_1","DOI":"10.1145\/1066157.1066289"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_6_1","DOI":"10.1109\/ICDE.2008.4497503"},{"key":"e_1_3_2_1_7_1","volume-title":"UW-Madison","author":"Chen F.","year":"2009","unstructured":"F. Chen , B. J. Gao , A. Doan , J. Yang , and R. Ramakrishnan . Optimizing complex extraction programs over evolving text data. Technical report , UW-Madison , 2009 . Availableat http:\/\/www.cs.wisc.edu\/~fchen\/delex-tr.pdf F. Chen, B. J. Gao, A. Doan, J. Yang, and R. Ramakrishnan. Optimizing complex extraction programs over evolving text data. Technical report, UW-Madison, 2009. Availableat http:\/\/www.cs.wisc.edu\/~fchen\/delex-tr.pdf"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_8_1","DOI":"10.1145\/958942.958945"},{"unstructured":"E. Chu A. Baid T. Chen A. Doan and J. Naughton. A relational approach to incrementally extracting and querying structure in unstructured data. VLDB-07.   E. Chu A. Baid T. Chen A. Doan and J. Naughton. A relational approach to incrementally extracting and querying structure in unstructured data. VLDB-07.","key":"e_1_3_2_1_9_1"},{"unstructured":"W. Cohen and A. McCallum. Information extraction from the world wide web(tutorial). KDD-03.  W. Cohen and A. McCallum. Information extraction from the world wide web(tutorial). KDD-03.","key":"e_1_3_2_1_10_1"},{"unstructured":"H. Cunningham D. Maynard K. Bontcheva and V. Tablan. GATE:A framework and graphical development environment for robust NLP tools and applications. ACL-02.  H. Cunningham D. Maynard K. Bontcheva and V. Tablan. GATE:A framework and graphical development environment for robust NLP tools and applications. ACL-02.","key":"e_1_3_2_1_11_1"},{"unstructured":"P. DeRose W. Shen F. Chen A. Doan and R. Ramakrishnan. Building structured web community portals: A top-down compositional and incremental approach. VLDB-07.   P. DeRose W. Shen F. Chen A. Doan and R. Ramakrishnan. Building structured web community portals: A top-down compositional and incremental approach. VLDB-07.","key":"e_1_3_2_1_12_1"},{"unstructured":"P. DeRose W. Shen F. Chen Y. Lee D. Burdick A. Doan and R. Ramakrishnan. DBLife: A community information management platform for the database research community (demo). CIDR-07.  P. DeRose W. Shen F. Chen Y. Lee D. Burdick A. Doan and R. Ramakrishnan. DBLife: A community information management platform for the database research community (demo). CIDR-07.","key":"e_1_3_2_1_13_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_14_1","DOI":"10.1145\/1519103.1519106"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_15_1","DOI":"10.1145\/1142473.1142595"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_16_1","DOI":"10.1145\/371920.371960"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_17_1","DOI":"10.1017\/S1351324904003523"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_18_1","DOI":"10.5555\/310709"},{"unstructured":"M. Herscovici R. Lempel and S. Yogev. Efficient indexing of versioned document sequences. ECIR-07.   M. Herscovici R. Lempel and S. Yogev. Efficient indexing of versioned document sequences. ECIR-07.","key":"e_1_3_2_1_19_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_20_1","DOI":"10.1145\/1142473.1142504"},{"unstructured":"A. Jain A. Doan and L. Gravano. SQL queries over unstructured text batabases. ICDE-07.  A. Jain A. Doan and L. Gravano. SQL queries over unstructured text batabases. ICDE-07.","key":"e_1_3_2_1_21_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_22_1","DOI":"10.1145\/1519103.1519110"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_23_1","DOI":"10.1145\/775152.775167"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_24_1","DOI":"10.1007\/BF01840446"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_25_1","DOI":"10.1109\/ICDE.2008.4497502"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_26_1","DOI":"10.1561\/1900000003"},{"unstructured":"S. Satpal and S. Sarawagi. Domain adaptation of conditional probability models via feature subsetting. ECML\/PKDD-07.  S. Satpal and S. Sarawagi. Domain adaptation of conditional probability models via feature subsetting. ECML\/PKDD-07.","key":"e_1_3_2_1_27_1"},{"unstructured":"W. Shen A. Doan J. F. Naughton and R. Ramakrishnan. Declarative information extraction using datalog with embedded extraction predicates. VLDB-07.   W. Shen A. Doan J. F. Naughton and R. Ramakrishnan. Declarative information extraction using datalog with embedded extraction predicates. VLDB-07.","key":"e_1_3_2_1_28_1"},{"unstructured":"D. S. Weld F. Wu E. Adar S. Amershi J. Fogarty R. Hoffmann K. Patel and M. Skinner. Intelligence in wikipedia. AAAI-08.   D. S. Weld F. Wu E. Adar S. Amershi J. Fogarty R. Hoffmann K. Patel and M. Skinner. Intelligence in wikipedia. AAAI-08.","key":"e_1_3_2_1_29_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_30_1","DOI":"10.1145\/1321440.1321449"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_31_1","DOI":"10.1145\/1242572.1242628"}],"event":{"sponsor":["SIGMOD ACM Special Interest Group on Management of Data","ACM Association for Computing Machinery"],"acronym":"SIGMOD\/PODS '09","name":"SIGMOD\/PODS '09: International Conference on Management of Data","location":"Providence Rhode Island USA"},"container-title":["Proceedings of the 2009 ACM SIGMOD International Conference on Management of data"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1559845.1559881","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/1559845.1559881","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T12:18:12Z","timestamp":1750249092000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1559845.1559881"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2009,6,29]]},"references-count":31,"alternative-id":["10.1145\/1559845.1559881","10.1145\/1559845"],"URL":"https:\/\/doi.org\/10.1145\/1559845.1559881","relation":{},"subject":[],"published":{"date-parts":[[2009,6,29]]},"assertion":[{"value":"2009-06-29","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}