{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T15:30:32Z","timestamp":1759332632368},"reference-count":23,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2007,6,22]],"date-time":"2007-06-22T00:00:00Z","timestamp":1182470400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Knowl Inf Syst"],"published-print":{"date-parts":[[2008,6]]},"DOI":"10.1007\/s10115-007-0085-3","type":"journal-article","created":{"date-parts":[[2007,6,21]],"date-time":"2007-06-21T02:25:20Z","timestamp":1182392720000},"page":"285-320","source":"Crossref","is-referenced-by-count":18,"title":["Boosting text segmentation via progressive classification"],"prefix":"10.1007","volume":"15","author":[{"given":"Eugenio","family":"Cesario","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Francesco","family":"Folino","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Antonio","family":"Locane","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Giuseppe","family":"Manco","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Riccardo","family":"Ortale","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2007,6,22]]},"reference":[{"key":"85_CR1","doi-asserted-by":"crossref","unstructured":"Adelberg B (1998). NoDoSE: A tool for semi-automatically extracting semistructured data from text documents. In: Haas LM, Tiwary A (eds) Proceedings of 1998 ACM SIGMOD conference on management of data. ACM Press, Seattle, WA, USA, June 1998, pp 283\u2013294","DOI":"10.1145\/276304.276330"},{"key":"85_CR2","doi-asserted-by":"crossref","unstructured":"Agichtein E, Ganti V (2004) Mining reference tables for automatic text segmentation. In: Kim W, Kohavi R, Gehrke J, DuMouchel W (eds) Proceedings of 2004 ACM SIGKDD conference on knowledge discovery and data mining. ACM Press, Seattle, WA, USA, August 2004, pp 20\u201329","DOI":"10.1145\/1014052.1014058"},{"key":"85_CR3","doi-asserted-by":"crossref","unstructured":"Borkar VR, Deshmukh K, Sarawagi S (2001) Automatic segmentation of text into structured records. In: Aref WG (ed) Proceedings of 2001 ACM SIGMOD conference on management of Data. ACM Press, Santa Barbara, CA, USA, May 2001, pp 175\u2013186","DOI":"10.1145\/375663.375682"},{"issue":"4","key":"85_CR4","first-page":"543","volume":"21","author":"E Brill","year":"1995","unstructured":"Brill E (1995). Transformation-based error-driven learning and natural language processing: a cased study in POS tagging. Comput Linguist 21(4): 543\u2013565","journal-title":"Comput Linguist"},{"key":"85_CR5","unstructured":"Califf ME, Mooney RJ (1999) Relational learning of pattern-match rules for information extraction. In: Proceedings of 16th national conference on artificial intelligence. AAAI\/MIT Press, Madison, WI, USA, July 1999, pp 328\u2013334"},{"key":"85_CR6","unstructured":"Cohen WW (1995) Learning to classify english text with ILP methods. In: De Raedt L (ed). Proceedings of the 5th international Workshop on inductive logic programming. Katholieke Universiteit Leuven, Haverlee, Belgium, pp 3\u201324"},{"issue":"1","key":"85_CR7","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TKDE.2007.250581","volume":"19","author":"AK Elmagarmid","year":"2007","unstructured":"Elmagarmid AK, Panagiotis GI and Verykios VS (2007). Duplicate Record Dectection: A Survey. IEEE Trans Knowl Data Eng 19(1): 1\u201316","journal-title":"IEEE Trans Knowl Data Eng"},{"issue":"2","key":"85_CR8","first-page":"57","volume":"17","author":"F Flesca","year":"2004","unstructured":"Flesca F, Manco G and Masciari E (2004). Web wrapper induction: a brief survey. AI Commun 17(2): 57\u201361","journal-title":"AI Commun"},{"key":"85_CR9","unstructured":"Freitag D (1998) Toward general-purpose learning for information extraction. In: Proceedings of 17th national conference on computational linguistics. ACL\/Morgan Kaufmann Publishers, Universit de Montral, Montreal, Quebec, Canada, August 1998, pp 404\u2013408"},{"key":"85_CR10","unstructured":"Gu L, Baxter RA, Vickers D et\u00a0al (2003) Record linkage: current practice and future directions. Technical report. CSIRO Mathematical and Information Sciences, Australia"},{"issue":"1","key":"85_CR11","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1023\/A:1009761603038","volume":"2","author":"MA Hern\u00e1ndez","year":"1998","unstructured":"Hern\u00e1ndez MA and Stolfo J (1998). Real-world data is dirty: data cleansing and the merge\/purge problem. Data Mining Knowl Discov 2(1): 9\u201337","journal-title":"Data Mining Knowl Discov"},{"key":"85_CR12","unstructured":"Junker M, Sintek M, Rinck M (1999) Learning for text categorization and information Extraction with ILP. In: Cussens J, Dzeroski S (eds) Learning language in logic. Springer Heidelberg, pp 247\u2013258"},{"issue":"3","key":"85_CR13","doi-asserted-by":"crossref","first-page":"225","DOI":"10.1016\/0885-2308(92)90019-Z","volume":"6","author":"J Kupiec","year":"1992","unstructured":"Kupiec J (1992). Robust part-of-speech tagging using a hidden Markov model. Comput Speech Lang 6(3): 225\u2013242","journal-title":"Comput Speech Lang"},{"key":"85_CR14","unstructured":"Lafferty JD, McCallum A, Pereira FCN (2001) Conditional random fields: probabilistic models for segmenting and labeling sequence data. In: Brodley CE, Pohoreckyj Danyluk A (eds). Proceedings of 18th international conference on machine learning. Morgan Kaufmann, Williamstown, MA, USA, June 2001, pp 282\u2013289"},{"key":"85_CR15","unstructured":"Liu B, Hsu W, Ma Y (1998) Integrating classification and association rule mining. In: Agrawal R, Stolorz PE, Piatetsky-Shapiro G (eds) Proceedings of 4th ACM SIGKDD international conference on knowledge discovery and data mining. AAAI Press, New York City, NY, USA, August 1998, pp 80\u201386"},{"key":"85_CR16","volume-title":"Foundations of statistical natural language processing","author":"CD Manning","year":"1999","unstructured":"Manning CD and Schultze C (1999). Foundations of statistical natural language processing. MIT Press, Cambridge"},{"issue":"1","key":"85_CR17","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1023\/A:1007673816718","volume":"39","author":"L Marquez","year":"2000","unstructured":"Marquez L, Padro L and Rodriguez H (2000). A machine learning approach to POS tagging. Mach Learn 39(1): 59\u201391","journal-title":"Mach Learn"},{"key":"85_CR18","unstructured":"McCallum A (2002) MALLET: a machine learning for language toolkit. http:\/\/mallet.cs.umass.edu"},{"key":"85_CR19","unstructured":"McCallum A, Freitag D, Pereira F (2000) Maximum entropy Markov models for information extraction and segmentation. In: Langley P (ed) Proceedings of 17th international conference on machine learning. Morgan Kaufmann, Standford University, Standord, CA, USA, June 2000, pp 591\u2013598"},{"key":"85_CR20","doi-asserted-by":"crossref","unstructured":"Mukherjee S, Ramakrishnan IV (2004) Taming the unstructured: creating structured content from partially labeled schematic text sequences. In: Meersman R, Tari Z (eds) Proceedings of 12th CoopIS\/DOA\/ ODBASE international conference. Springer, Agia Napa, Cyprus, October 2004, pp 909\u2013926","DOI":"10.1007\/978-3-540-30469-2_6"},{"key":"85_CR21","doi-asserted-by":"crossref","first-page":"233","DOI":"10.1023\/A:1007562322031","volume":"34","author":"S Soderland","year":"1999","unstructured":"Soderland S (1999). Learning information extraction rules for semi\/structured and free text. Mach Learn 34: 233\u2013272","journal-title":"Mach Learn"},{"key":"85_CR22","unstructured":"Srikant R, Agrawal R (1995) Mining generalized association rules. In: Dayal U, Gray PMD, Nishio S (eds) Proceedings of 21th international conference on Very large databases. Morgan Kaufmann, Zurich, Switzerland, September 1995, pp 407\u2013419"},{"key":"85_CR23","unstructured":"Winkler WE (1999) The state of record linkage and current research problems. Technical report. Statistical Research Division, U.S. Census Bureau, Wachington, DC"}],"container-title":["Knowledge and Information Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10115-007-0085-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10115-007-0085-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10115-007-0085-3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,29]],"date-time":"2019-05-29T06:10:16Z","timestamp":1559110216000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10115-007-0085-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2007,6,22]]},"references-count":23,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2008,6]]}},"alternative-id":["85"],"URL":"https:\/\/doi.org\/10.1007\/s10115-007-0085-3","relation":{},"ISSN":["0219-1377","0219-3116"],"issn-type":[{"value":"0219-1377","type":"print"},{"value":"0219-3116","type":"electronic"}],"subject":[],"published":{"date-parts":[[2007,6,22]]}}}