{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T04:31:34Z","timestamp":1750307494993,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":18,"publisher":"ACM","license":[{"start":{"date-parts":[[2010,10,26]],"date-time":"2010-10-26T00:00:00Z","timestamp":1288051200000},"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":[[2010,10,26]]},"DOI":"10.1145\/1871840.1871845","type":"proceedings-article","created":{"date-parts":[[2010,10,28]],"date-time":"2010-10-28T14:43:19Z","timestamp":1288276999000},"page":"19-26","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":12,"title":["Extracting person names from diverse and noisy OCR text"],"prefix":"10.1145","author":[{"given":"Thomas L.","family":"Packer","sequence":"first","affiliation":[{"name":"Brigham Young University, Provo, UT, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joshua F.","family":"Lutes","sequence":"additional","affiliation":[{"name":"Brigham Young University, Provo, UT, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aaron P.","family":"Stewart","sequence":"additional","affiliation":[{"name":"Brigham Young University, Provo, UT, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David W.","family":"Embley","sequence":"additional","affiliation":[{"name":"Brigham Young University, Provo, UT, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eric K.","family":"Ringger","sequence":"additional","affiliation":[{"name":"Brigham Young University, Provo, UT, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kevin D.","family":"Seppi","sequence":"additional","affiliation":[{"name":"Brigham Young University, Provo, UT, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lee S.","family":"Jensen","sequence":"additional","affiliation":[{"name":"Ancestry.com, Inc., Provo, UT, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2010,10,26]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.3115\/1119176.1119199"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-12116-6_9"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0169-023X(99)00027-0"},{"key":"e_1_3_2_1_4_1","volume-title":"Proceedings of the 6th International Conference on Language Resources and Evaluation (LREC 2008)","author":"Grover C.","year":"2008","unstructured":"C. Grover , S. Givon , R. Tobin , and J. Ball . Named entity recognition for digitised historical texts . In Proceedings of the 6th International Conference on Language Resources and Evaluation (LREC 2008) , 2008 . C. Grover, S. Givon, R. Tobin, and J. Ball. Named entity recognition for digitised historical texts. In Proceedings of the 6th International Conference on Language Resources and Evaluation (LREC 2008), 2008."},{"key":"e_1_3_2_1_5_1","unstructured":"Kofax. Kofax homepage. http:\/\/www.kofax.com\/ 2009.  Kofax. Kofax homepage. http:\/\/www.kofax.com\/ 2009."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/1555400.1555437"},{"key":"e_1_3_2_1_7_1","unstructured":"A. K. McCallum. MALLET: a machine learning for language toolkit. http:\/\/mallet.cs.umass.edu\/ 2002.  A. K. McCallum. MALLET: a machine learning for language toolkit. http:\/\/mallet.cs.umass.edu\/ 2002."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.3115\/974147.974191"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.3115\/1119176.1119207"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1075\/li.30.1.03nad"},{"key":"e_1_3_2_1_11_1","unstructured":"PrimeRecognition. PrimeOCR web page. http:\/\/www.primerecognition.com\/augprime\/prime ocr.htm 2009.  PrimeRecognition. PrimeOCR web page. http:\/\/www.primerecognition.com\/augprime\/prime ocr.htm 2009."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.5555\/1596374.1596399"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.3115\/1119176.1119195"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1002\/asi.v60:8"},{"key":"e_1_3_2_1_15_1","first-page":"181","volume-title":"Entity extraction is a boring solved problem: or is it? In Human Language Technologies 2007: The Conference of the North American","author":"Vilain M.","year":"2007","unstructured":"M. Vilain , J. Su , and S. Lubar . Entity extraction is a boring solved problem: or is it? In Human Language Technologies 2007: The Conference of the North American Chapter of the Association for Computational Linguistics; Companion Volume, Short Papers on XX, pages 181 -- 184 . Association for Computational Linguistics , 2007 . M. Vilain, J. Su, and S. Lubar. Entity extraction is a boring solved problem: or is it? In Human Language Technologies 2007: The Conference of the North American Chapter of the Association for Computational Linguistics; Companion Volume, Short Papers on XX, pages 181--184. Association for Computational Linguistics, 2007."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/1559845.1559925"},{"key":"e_1_3_2_1_17_1","first-page":"142","volume-title":"Proceedings of the 5th SIGHAN Workshop on Chinese Language Processing","author":"Wu C. W.","year":"2006","unstructured":"C. W. Wu , S. Y. Jan , R. T. H. Tsai , and W. L. Hsu . On using ensemble methods for chinese named entity recognition . In Proceedings of the 5th SIGHAN Workshop on Chinese Language Processing , pages 142 -- 145 , 2006 . C. W. Wu, S. Y. Jan, R. T. H. Tsai, and W. L. Hsu. On using ensemble methods for chinese named entity recognition. In Proceedings of the 5th SIGHAN Workshop on Chinese Language Processing, pages 142--145, 2006."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/1815330.1815346"}],"event":{"name":"CIKM '10: International Conference on Information and Knowledge Management","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data","SIGIR ACM Special Interest Group on Information Retrieval"],"location":"Toronto ON Canada","acronym":"CIKM '10"},"container-title":["Proceedings of the fourth workshop on Analytics for noisy unstructured text data"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1871840.1871845","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/1871840.1871845","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T12:17:38Z","timestamp":1750249058000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1871840.1871845"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010,10,26]]},"references-count":18,"alternative-id":["10.1145\/1871840.1871845","10.1145\/1871840"],"URL":"https:\/\/doi.org\/10.1145\/1871840.1871845","relation":{},"subject":[],"published":{"date-parts":[[2010,10,26]]},"assertion":[{"value":"2010-10-26","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}