{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T10:10:54Z","timestamp":1775297454728,"version":"3.50.1"},"publisher-location":"New York, NY","reference-count":31,"publisher":"Springer New York","isbn-type":[{"value":"9781461482666","type":"print"},{"value":"9781461482659","type":"electronic"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-1-4614-8265-9_459","type":"book-chapter","created":{"date-parts":[[2018,12,6]],"date-time":"2018-12-06T07:41:17Z","timestamp":1544082077000},"page":"4620-4629","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Web Information Extraction"],"prefix":"10.1007","author":[{"given":"Laura","family":"Chiticariu","sequence":"first","affiliation":[]},{"given":"Marina","family":"Danilevsky","sequence":"additional","affiliation":[]},{"given":"Howard","family":"Ho","sequence":"additional","affiliation":[]},{"given":"Rajasekar","family":"Krishnamurthy","sequence":"additional","affiliation":[]},{"given":"Yunyao","family":"Li","sequence":"additional","affiliation":[]},{"given":"Sriram","family":"Raghavan","sequence":"additional","affiliation":[]},{"given":"Frederick","family":"Reiss","sequence":"additional","affiliation":[]},{"given":"Shivakumar","family":"Vaithyanathan","sequence":"additional","affiliation":[]},{"given":"Huaiyu","family":"Zhu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,12,7]]},"reference":[{"key":"459_CR2398","unstructured":"Akbik A, Konomi O, Melnikov M. Propminer: a workflow for interactive information extraction and exploration using dependency trees. In: Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics; 2013."},{"key":"459_CR2399","doi-asserted-by":"crossref","unstructured":"Appelt DE, Onyshkevych B. The common pattern specification language. In: Proceedings of the TIPSTER Text Program: Phase III. 1998.","DOI":"10.21236\/ADA631525"},{"key":"459_CR23100","doi-asserted-by":"crossref","unstructured":"Atasu K, Polig R, Hagleitner C, Reiss FR. Hardware-accelerated regular expression matching for high-throughput text analytics. In: Proceedings of the 23rd International Conference on Field programmable Logic and Applications; 2013. p. 1\u20137.","DOI":"10.1109\/FPL.2013.6645534"},{"key":"459_CR23101","doi-asserted-by":"crossref","unstructured":"Boguraev B. Annotation-based finite state processing in a large-scale NLP architecture. In: Proceedings of the International Conference on Recent Advances in Natural Language Processing. 2003.","DOI":"10.1075\/cilt.260.07bog"},{"issue":"4","key":"459_CR23102","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1145\/1519103.1519107","volume":"37","author":"P Bohannon","year":"2008","unstructured":"Bohannon P, Merugu S, Yu C, Agarwal V, DeRose P, Iyer AS, Jain A, Kakade V, Muralidharan M, Ramakrishnan R, Shen W. Purple sox extraction management system. SIGMOD Rec. 2008;37(4):21\u201327.","journal-title":"SIGMOD Rec"},{"key":"459_CR23103","doi-asserted-by":"crossref","unstructured":"Brauer F, Rieger R, Mocan A, Barczynski WM. Enabling information extraction by inference of regular expressions from sample entities. In: Proceedings of the 20th ACM International Conference on Information and Knowledge Management; 2011.","DOI":"10.1145\/2063576.2063763"},{"issue":"3","key":"459_CR23104","first-page":"60","volume":"34","author":"D Burdick","year":"2011","unstructured":"Burdick D, Hern\u00e1ndez M, Ho H, Koutrika G, Krishnamurthy R, Popa L, Stanoi IR, Vaithyanathan S, Das S. Extracting, linking and integrating data from public sources: a financial case study. IEEE Data Eng Bull. 2011;34(3):60\u201367.","journal-title":"IEEE Data Eng Bull"},{"key":"459_CR23105","doi-asserted-by":"crossref","unstructured":"Cafarella MJ, Etzion O. A search engine for natural language applications. In: Proceedings of the 14th International World Wide Web Conference; 2005.","DOI":"10.1145\/1060745.1060811"},{"key":"459_CR23106","unstructured":"Chiticariu L, Krishnamurthy R, Li Y, Raghavan S, Reiss F, Vaithyanathan S. Systemt: an algebraic approach to declarative information extraction. In: Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics; 2010."},{"key":"459_CR23107","unstructured":"Chiticariu L, Krishnamurthy R, Li Y, Reiss F, Vaithyanathan S. Domain adaptation of rule-based annotators for named-entity recognition tasks. In: Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing; 2010."},{"key":"459_CR23108","doi-asserted-by":"crossref","unstructured":"Chiticariu L, Li Y, Reiss FR. Rule-based information extraction is dead! long live rule-based information extraction systems! In: Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing; 2013.","DOI":"10.18653\/v1\/D13-1079"},{"key":"459_CR23109","unstructured":"Cohen W, McCallum A. Information extraction from the world wide web. In: Proceedings of the 9th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining; 2003."},{"key":"459_CR23110","doi-asserted-by":"publisher","first-page":"665","DOI":"10.1016\/B0-08-044854-2\/00960-3","volume-title":"Encyclopedia of Language & Linguistics","author":"H. Cunningham","year":"2006","unstructured":"Cunningham H. Information extraction, automatic. In: Encyclopedia of language and linguistics. 2nd ed. Elsevier; Amsterdam. 2005."},{"key":"459_CR23111","doi-asserted-by":"crossref","unstructured":"Doan A, Ramakrishnan R, Vaithyanathan S. Managing information extraction: state of the art and research directions. In: Proceedings of the ACM SIGMOD International Conference on Management of Data; 2006.","DOI":"10.1145\/1142473.1142595"},{"key":"459_CR23112","doi-asserted-by":"crossref","unstructured":"Grishman R, Sundheim B. Message understanding conference-6: a brief history. In: Proceedings of the 16th International Conference on Computational Linguistics; 1996.","DOI":"10.3115\/992628.992709"},{"issue":"1","key":"459_CR23113","doi-asserted-by":"publisher","first-page":"736","DOI":"10.14778\/1453856.1453936","volume":"1","author":"Jiansheng Huang","year":"2008","unstructured":"Huang J, Chen T, Doan A, Naughton JF. On the provenance of non-answers to queries over extracted data. Proc VLDB Endow;1(1):736\u2013747","journal-title":"Proceedings of the VLDB Endowment"},{"key":"459_CR23114","unstructured":"Lafferty J, McCallum A, Pereira F. Conditional random fields: probabilistic models for segmenting and labeling sequence data. In: Proceedings of the 18th International Conference on Machine Learning; 2001."},{"key":"459_CR23115","doi-asserted-by":"crossref","unstructured":"Li Y, Chu V, Blohm S, Zhu H, Ho H. Facilitating pattern discovery for relation extraction with semantic-signature-based clustering. In: Proceedings of the 20th ACM International Conference on Information and Knowledge Management; 2011.","DOI":"10.1145\/2063576.2063781"},{"key":"459_CR23116","doi-asserted-by":"crossref","unstructured":"Li Y, Krishnamurthy R, Raghavan S, Vaithyanathan S, Jagadish HV. Regular expression learning for information extraction. In: Proceedings of the 2008 Conference on Empirical Methods in Natural Language Processing; 2008.","DOI":"10.3115\/1613715.1613719"},{"key":"459_CR23117","doi-asserted-by":"crossref","unstructured":"Li Y, Krishnamurthy R, Vaithyanathan S, Jagadish H. Getting work done on the web: supporting transactional queries. In: Proceedings of the 29th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval; 2006.","DOI":"10.1145\/1148170.1148266"},{"issue":"1-2","key":"459_CR23118","doi-asserted-by":"publisher","first-page":"588","DOI":"10.14778\/1920841.1920916","volume":"3","author":"Bin Liu","year":"2010","unstructured":"Liu B, Chiticariu L, Chu V, Jagadish HV, Reiss F. Automatic rule refinement for information extraction.: Proc VLDB Endow. 2010;3(1):588\u201397.","journal-title":"Proceedings of the VLDB Endowment"},{"key":"459_CR23119","unstructured":"Nagesh A, Ramakrishnan G, Chiticariu L, Krishnamurthy R, Dharkar A, Bhattacharyya P. Towards efficient named-entity rule induction for customizability. In: Proceedings of the 2012 Conference on Empirical Methods on Natural Language Processing and Computational Natural Language Learning; 2012."},{"key":"459_CR23120","doi-asserted-by":"crossref","unstructured":"Reiss F, Raghavan S, Krishnamurthy R, Zhu H, Vaithyanathan S. An algebraic approach to rule-based information extraction. In: Proceedings of the 24th International Conference on Data Engineering; 2008.","DOI":"10.1109\/ICDE.2008.4497502"},{"key":"459_CR23121","unstructured":"Riloff E. Automatically constructing a dictionary for information extraction tasks. In: Proceedings of the 11th National Conference on Artificial Intelligence; 1993."},{"key":"459_CR23122","doi-asserted-by":"crossref","unstructured":"Roy S, Chiticariu L, Feldman V, Reiss F, Zhu H. Provenance-based dictionary refinement in information extraction. In: Proceedings of the ACM SIGMOD International Conference on Management of Data; 2013.","DOI":"10.1145\/2463676.2465284"},{"key":"459_CR23123","unstructured":"Sarma AD, Jain A, Bohannon P. Building a generic debugger for information extraction pipelines. In: Proceedings of the 20th ACM International Conference on Information and Knowledge Management; 2011."},{"key":"459_CR23124","volume-title":"I4e: interactive investigation of iterative information extraction","author":"AD Sarma","year":"2010","unstructured":"Sarma AD, Jain A, Srivastava D. I4e: interactive investigation of iterative information extraction. In: Proceedings of the ACM SIGMOD International Conference on Management of Data; 2010."},{"key":"459_CR23125","unstructured":"Shen W, Doan A, Naughton J, Ramakrishnan R. Declarative information extraction using datalog with embedded extraction predicates. In: Proceedings of the 33rd International Conference on Very Large Data Bases; 2007."},{"issue":"1","key":"459_CR23126","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1145\/2627692.2627706","volume":"43","author":"S Wandelt","year":"2014","unstructured":"Wandelt S, Deng D, Gerdjikov S, Mishra S, Mitankin P, Patil M, Siragusa E, Tiskin A, Wang W, Wang J, Leser U. State-of-the-art in string similarity search and join. SIGMOD Rec. 2014;43(1):64\u201376.","journal-title":"SIGMOD Rec"},{"key":"459_CR23127","doi-asserted-by":"crossref","unstructured":"Wang DZ, Wei L, Li Y, Reiss F, Vaithyanathan S. Selectivity estimation for extraction operators over text data. In: Proceedings of the 27th International Conference on Data Engineering; 2011.","DOI":"10.1109\/ICDE.2011.5767931"},{"key":"459_CR23128","unstructured":"Zhang C, Baldwin T, Ho H, Kimelfeld B, Li Y. Adaptive parser-centric text normalization. In: Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics; 2013. p. 1159\u201368."}],"container-title":["Encyclopedia of Database Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-1-4614-8265-9_459","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T09:42:17Z","timestamp":1775295737000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-1-4614-8265-9_459"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9781461482666","9781461482659"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-1-4614-8265-9_459","relation":{},"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"7 December 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}