{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T16:41:06Z","timestamp":1758127266935},"publisher-location":"Berlin, Heidelberg","reference-count":18,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540321408"},{"type":"electronic","value":"9783540321576"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2006]]},"DOI":"10.1007\/11669487_31","type":"book-chapter","created":{"date-parts":[[2006,1,19]],"date-time":"2006-01-19T08:46:59Z","timestamp":1137660419000},"page":"348-357","source":"Crossref","is-referenced-by-count":18,"title":["The Effects of OCR Error on the Extraction of Private Information"],"prefix":"10.1007","author":[{"given":"Kazem","family":"Taghva","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Russell","family":"Beckley","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jeffrey","family":"Coombs","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"31_CR1","unstructured":"U.S. Government. The freedom of information act 5 U.S.C. sec. 552 as amended in 2002 (Viewed June 30 2004), http:\/\/www.usdoj.gov\/oip\/foia_updates\/Vol_XVII_4\/page2.htm"},{"key":"31_CR2","unstructured":"U.S. Government. Frequently occurring first names and surnames from the 1990 census (Viewed August, 2005), http:\/\/www.census.gov\/genealogy\/www\/freqnames.html"},{"key":"31_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1007\/3-540-63438-X_2","volume-title":"Information Extraction","author":"R. Grishman","year":"1997","unstructured":"Grishman, R.: Information extraction: Techniques and challenges. In: Pazienza, M.T. (ed.) SCIE 1997. LNCS, vol.\u00a01299, pp. 10\u201327. Springer, Heidelberg (1997)"},{"key":"31_CR4","doi-asserted-by":"crossref","unstructured":"Jing, H., Lopresti, D., Shih, C.: Summarizing noisy documents. In: Proceedings of SDIUT 2003, Greenbelt, MD, April 2003, pp. 111\u2013119 (2003)","DOI":"10.3115\/1119467.1119471"},{"key":"31_CR5","unstructured":"McCallum, A.: Bow: A toolkit for statistical language modeling, text retrieval, classification and clustering (1996), http:\/\/www.cs.cmu.edu\/~mccallum\/bow"},{"key":"31_CR6","volume-title":"Statistics for Engineering and the Sciences","author":"W. Mendenhall","year":"1995","unstructured":"Mendenhall, W., Sincich, T.: Statistics for Engineering and the Sciences, 4th edn. Prentice Hall, Englewood Cliffs (1995)","edition":"4"},{"key":"31_CR7","doi-asserted-by":"crossref","unstructured":"Miller, D., Boisen, S., Schwartz, R., Stone, R., Weischedel, R.: Named entity extraction from noisy input: Speech and OCR. In: Proceedings of the Sixth Conference on Applied Natural Languae Processing, pp. 316\u2013324 (2000)","DOI":"10.3115\/974147.974191"},{"key":"31_CR8","doi-asserted-by":"crossref","unstructured":"Mooney, R., Bunescu, R.: Mining knowledge from text using information extraction. In: SIGKDD Explorations, June 2005, vol.\u00a07, pp. 3\u201310 (2005)","DOI":"10.1145\/1089815.1089817"},{"key":"31_CR9","doi-asserted-by":"crossref","unstructured":"Nartker, T., Taghva, K., Young, R., Borsack, J., Condit, A.: OCR correction based on document level knowledge. In: Proc. IS&T\/SPIE 2003 Intl. Symp. on Electronic Imaging Science and Technology, Santa Clara, CA, January 2003, vol.\u00a05010, pp. 103\u2013110 (2003)","DOI":"10.1117\/12.479681"},{"key":"31_CR10","volume-title":"Fundamentals of Speech Recognition","author":"L. Rabiner","year":"1993","unstructured":"Rabiner, L., Juang, B.-H.: Fundamentals of Speech Recognition. Prentice Hall, Englewood Cliffs (1993)"},{"key":"31_CR11","doi-asserted-by":"crossref","unstructured":"Taghva, K., Beckley, R., Coombs, J., Borsack, J., Pereda, R., Nartker, T.: Automatic redaction of private information using relational information extraction. In: Proc. IS&T\/SPIE 2006 Intl. Symp. on Electronic Imaging Science and Technology (2006) (Submitted)","DOI":"10.1117\/12.643126"},{"key":"31_CR12","unstructured":"Taghva, K., Borsack, J., Nartker, T.: A process flow for realizing high accuracy for ocr text. In: SDIUT 2006 (2006) (Forthcoming)"},{"key":"31_CR13","unstructured":"Taghva, K., Cartright, M.: An efficient tool for XML data preparation. In: Proc. ISNG 2005 Information Systems: New Generations, Las Vegas, NV (April 2005)"},{"key":"31_CR14","doi-asserted-by":"crossref","unstructured":"Taghva, K., Coombs, J., Pereda, R.: Address extraction using hidden markov models. In: Proc. IS&T\/SPIE 2005 Intl. Symp. on Electronic Imaging Science and Technology, San Jose, CA (January 2005)","DOI":"10.1117\/12.587799"},{"key":"31_CR15","doi-asserted-by":"crossref","unstructured":"Taghva, K., Nartker, T., Borsack, J.: Information access in the presence of OCR errors. In: Proc. of ACM Hardcopy Document Processing Workshop, Washington, DC, November 2004, pp. 1\u20138 (2004)","DOI":"10.1145\/1031442.1031443"},{"key":"31_CR16","unstructured":"Taghva, K., Nartker, T.A., Borsack, J.: Recognize, categorize, and retrieve. In: Proc. of the Symposium on Document Image Understanding Technology, Columbia, MD, April 2001, pp. 227\u2013232 (2001), Laboratory for Language and Media Processing, University of Maryland"},{"key":"31_CR17","doi-asserted-by":"crossref","unstructured":"Taghva, K., Nartker, T., Borsack, J., Lumos, S., Condit, A., Young, R.: Evaluating text categorization in the presence of OCR errors. In: Proc. IS&T\/SPIE 2001 Intl. Symp. on Electronic Imaging Science and Technology, San Jose, CA, January 2001, pp. 68\u201374 (2001)","DOI":"10.1117\/12.410861"},{"issue":"3","key":"31_CR18","doi-asserted-by":"publisher","first-page":"125","DOI":"10.1007\/PL00013558","volume":"3","author":"K. Taghva","year":"2001","unstructured":"Taghva, K., Stofsky, E.: Ocrspell: An interactive spelling correction system for OCR errors in text. Intl. Journal on Document Analysis and Recognition\u00a03(3), 125\u2013137 (2001)","journal-title":"Intl. Journal on Document Analysis and Recognition"}],"container-title":["Lecture Notes in Computer Science","Document Analysis Systems VII"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/11669487_31.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,7,22]],"date-time":"2021-07-22T16:51:58Z","timestamp":1626972718000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/11669487_31"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2006]]},"ISBN":["9783540321408","9783540321576"],"references-count":18,"URL":"https:\/\/doi.org\/10.1007\/11669487_31","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2006]]}}}