{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T04:42:26Z","timestamp":1750308146284,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":35,"publisher":"ACM","license":[{"start":{"date-parts":[[2005,8,21]],"date-time":"2005-08-21T00:00:00Z","timestamp":1124582400000},"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":[[2005,8,21]]},"DOI":"10.1145\/1081870.1081926","type":"proceedings-article","created":{"date-parts":[[2005,11,7]],"date-time":"2005-11-07T17:34:39Z","timestamp":1131384879000},"page":"489-498","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":37,"title":["Email data cleaning"],"prefix":"10.1145","author":[{"given":"Jie","family":"Tang","sequence":"first","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hang","family":"Li","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunbo","family":"Cao","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhaohui","family":"Tang","sequence":"additional","affiliation":[{"name":"Microsoft Corporation, Redmond, WA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2005,8,21]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.5555\/234285.234289"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.3115\/1075218.1075255"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.5555\/777092.777213"},{"key":"e_1_3_2_1_4_1","first-page":"93","volume":"1","author":"Church K.","year":"1991","unstructured":"K. Church and W. Gale . Probability Scoring for Spelling Correction. In Statistics and Computing , Vol. 1 , 1991 , pages 93 -- 103 . K. Church and W. Gale. Probability Scoring for Spelling Correction. In Statistics and Computing, Vol. 1, 1991, pages 93--103.","journal-title":"Probability Scoring for Spelling Correction. In Statistics and Computing"},{"key":"e_1_3_2_1_5_1","volume-title":"Proc. of Workshop on Shallow Processing of Large Corpora. Corpus Linguistics 2003","author":"Clark A.","year":"2003","unstructured":"A. Clark . Pre-processing Very Noisy Text . In Proc. of Workshop on Shallow Processing of Large Corpora. Corpus Linguistics 2003 , Lancaster. 2003 . A. Clark. Pre-processing Very Noisy Text. In Proc. of Workshop on Shallow Processing of Large Corpora. Corpus Linguistics 2003, Lancaster. 2003."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.3115\/1118693.1118694"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022627411411"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/382899.383305"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"crossref","first-page":"429","DOI":"10.1007\/978-0-585-35958-8_22","volume-title":"Computational Linguistics: In Honour of Don Walker","author":"Gale W. A.","year":"1994","unstructured":"W. A. Gale , K. W. Church , and D. Yarowsky . 1994 . Discrimination Decisions for 100,000-Dimensional Spaces. Current Issues in Computational Linguistics: In Honour of Don Walker . Kluwer Academic Publishers , pages 429 -- 450 . W. A. Gale, K. W. Church, and D. Yarowsky. 1994. Discrimination Decisions for 100,000-Dimensional Spaces. Current Issues in Computational Linguistics: In Honour of Don Walker. Kluwer Academic Publishers, pages 429--450."},{"key":"e_1_3_2_1_10_1","volume-title":"Journees Bases de Donnees","author":"Galhardas H.","year":"2000","unstructured":"H. Galhardas , D. Florescu , D. Shasha , and E. Simon . Declaratively Cleaning Your Data Using AJAX . In Journees Bases de Donnees , Oct. 2000 . http:\/\/caravel.inria.fr\/~galharda\/BDA.ps. H. Galhardas, D. Florescu, D. Shasha, and E. Simon. Declaratively Cleaning Your Data Using AJAX. In Journees Bases de Donnees, Oct. 2000. http:\/\/caravel.inria.fr\/~galharda\/BDA.ps."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007425814087"},{"key":"e_1_3_2_1_12_1","volume-title":"Proc. of the 13th International Conference on Machine Learning (ICML","author":"Golding A. R.","year":"1996","unstructured":"A. R. Golding and D. Roth . Applying Winnow to Context-Sensitive Spelling Correction . In Proc. of the 13th International Conference on Machine Learning (ICML 1996 ). A. R. Golding and D. Roth. Applying Winnow to Context-Sensitive Spelling Correction. In Proc. of the 13th International Conference on Machine Learning (ICML 1996)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1009761603038"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/301136.301186"},{"key":"e_1_3_2_1_15_1","volume-title":"Proc. of ICML 01","author":"Lafferty J.","year":"2001","unstructured":"J. Lafferty , A. McCallum , and F. Pereira . Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data . In Proc. of ICML 01 , 2001 . J. Lafferty, A. McCallum, and F. Pereira. Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data. In Proc. of ICML 01, 2001."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/775047.775134"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.3115\/1075096.1075116"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/0306-4573(91)90066-U"},{"key":"e_1_3_2_1_19_1","volume-title":"Proc. of the ICML Coference","author":"McCallum A.","year":"2000","unstructured":"A. McCallum , D. Freitag , and F. Pereira . Maximum Entropy Markov Models for Information Extraction and Segmentation , In Proc. of the ICML Coference , 2000 . A. McCallum, D. Freitag, and F. Pereira. Maximum Entropy Markov Models for Information Extraction and Segmentation, In Proc. of the ICML Coference, 2000."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1162\/089120102760275992"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.3115\/1034678.1034746"},{"key":"e_1_3_2_1_22_1","first-page":"241","volume-title":"Adaptive Multilingual Sentence Boundary Disambiguation. Computational Linguistics","author":"Palmer D. D.","year":"1997","unstructured":"D. D. Palmer and M. A. Hearst . Adaptive Multilingual Sentence Boundary Disambiguation. Computational Linguistics . MIT Press Cambridge , MA , USA. Vol. 23, Issue 2 ( June 1997 ), pages 241 -- 267 . D. D. Palmer and M. A. Hearst. Adaptive Multilingual Sentence Boundary Disambiguation. Computational Linguistics. MIT Press Cambridge, MA, USA. Vol. 23, Issue 2 (June 1997), pages 241--267."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/276404.276408"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/860435.860479"},{"volume-title":"Data Cleaning: Problems and Current Approaches","author":"Rahm E.","key":"e_1_3_2_1_25_1","unstructured":"E. Rahm and H. H. Do . Data Cleaning: Problems and Current Approaches , IEEE Bulletin of the Technical Committee on Data Engineering , Vol. 23 No. 4, December 2000. E. Rahm and H. H. Do. Data Cleaning: Problems and Current Approaches, IEEE Bulletin of the Technical Committee on Data Engineering, Vol. 23 No. 4, December 2000."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.3115\/980691.980746"},{"key":"e_1_3_2_1_27_1","unstructured":"R. Sproat A. Black S. Chen S. Kumar M. Ostendorf and C. Richards. Normalization of non-standard words. WS'99 Final Report.http:\/\/www.clsp.jhu.edu\/ws99\/projects\/normal\/.  R. Sproat A. Black S. Chen S. Kumar M. Ostendorf and C. Richards. Normalization of non-standard words. WS'99 Final Report.http:\/\/www.clsp.jhu.edu\/ws99\/projects\/normal\/."},{"key":"e_1_3_2_1_28_1","volume-title":"Springer Verlage","author":"Vapnik V.","year":"1998","unstructured":"V. Vapnik . Statistical Learning Theroy . Springer Verlage , New York , 1998 . V. Vapnik. Statistical Learning Theroy. Springer Verlage, New York, 1998."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/511446.511478"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.3115\/1075218.1075233"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/956750.956785"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/1008992.1009042"},{"key":"e_1_3_2_1_33_1","unstructured":"J. Decker. eClean 2000 http:\/\/www.jd-software.com\/eClean2000\/index.html.  J. Decker. eClean 2000 http:\/\/www.jd-software.com\/eClean2000\/index.html."},{"key":"e_1_3_2_1_34_1","unstructured":"ListCleaner Pro. http:\/\/www.WinPure.com\/EmailCleaner.  ListCleaner Pro. http:\/\/www.WinPure.com\/EmailCleaner."},{"key":"e_1_3_2_1_35_1","unstructured":"Fuzzy Lookup and Fuzzy Grouping in Data Transformation Services for SQL Server 2005. http:\/\/msdn.microsoft.com\/library\/default.asp?url=\/library\/en-us\/dnsql90\/html\/FzDTSSQL05.asp  Fuzzy Lookup and Fuzzy Grouping in Data Transformation Services for SQL Server 2005. http:\/\/msdn.microsoft.com\/library\/default.asp?url=\/library\/en-us\/dnsql90\/html\/FzDTSSQL05.asp"}],"event":{"name":"KDD05: The Eleventh ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data","ACM Association for Computing Machinery"],"location":"Chicago Illinois USA","acronym":"KDD05"},"container-title":["Proceedings of the eleventh ACM SIGKDD international conference on Knowledge discovery in data mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1081870.1081926","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/1081870.1081926","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T16:18:37Z","timestamp":1750263517000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1081870.1081926"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2005,8,21]]},"references-count":35,"alternative-id":["10.1145\/1081870.1081926","10.1145\/1081870"],"URL":"https:\/\/doi.org\/10.1145\/1081870.1081926","relation":{},"subject":[],"published":{"date-parts":[[2005,8,21]]},"assertion":[{"value":"2005-08-21","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}