{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T06:18:10Z","timestamp":1775283490244,"version":"3.50.1"},"publisher-location":"New York, New York, USA","reference-count":38,"publisher":"ACM Press","license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1145\/3184558.3186582","type":"proceedings-article","created":{"date-parts":[[2018,4,18]],"date-time":"2018-04-18T18:04:25Z","timestamp":1524074665000},"page":"655-662","source":"Crossref","is-referenced-by-count":7,"title":["Automated Extractions for Machine Generated Mail"],"prefix":"10.1145","author":[{"given":"Dotan","family":"Di Castro","sequence":"first","affiliation":[{"name":"Yahoo! Reseaerch, Haifa, Israel"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Iftah","family":"Gamzu","sequence":"additional","affiliation":[{"name":"Amazon Research, Haifa, Israel"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Irena","family":"Grabovitch-Zuyev","sequence":"additional","affiliation":[{"name":"Yahoo! Reseaerch, Haifa, Israel"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liane","family":"Lewin-Eytan","sequence":"additional","affiliation":[{"name":"Amazon Research, Haifa, Israel"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Abhinav","family":"Pundir","sequence":"additional","affiliation":[{"name":"Yahoo! Inc., Sunnyvale, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nil Ratan","family":"Sahoo","sequence":"additional","affiliation":[{"name":"Yahoo! Inc., Sunnyvale, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael","family":"Viderman","sequence":"additional","affiliation":[{"name":"Yahoo! Reseaerch, Haifa, Israel"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","reference":[{"key":"key-10.1145\/3184558.3186582-1","doi-asserted-by":"crossref","unstructured":"C. C. Aggarwal and C. X. Zhai. Mining Text Data. Springer Publishing Company, Incorporated, 2012.","DOI":"10.1007\/978-1-4614-3223-4"},{"key":"key-10.1145\/3184558.3186582-2","doi-asserted-by":"crossref","unstructured":"N. Ailon, Z. S. Karnin, E. Liberty, and Y. Maarek. Threading machine generated email. In WSDM, pages 405--414, 2013.","DOI":"10.1145\/2433396.2433447"},{"key":"key-10.1145\/3184558.3186582-3","doi-asserted-by":"crossref","unstructured":"A. Arasu and H. Garcia-Molina. Extracting structured data from web pages. In ACM SIGMOD, pages 337--348, 2003.","DOI":"10.1145\/872757.872799"},{"key":"key-10.1145\/3184558.3186582-4","doi-asserted-by":"crossref","unstructured":"N. Avigdor-Elgrabli, M. Cwalinski, D. D. Castro, I. Gamzu, I. Grabovitch-Zuyev, L. Lewin-Eytan, and Y. Maarek. Structural clustering of machine-generated mail. In CIKM, pages 217--226, 2016.","DOI":"10.1145\/2983323.2983350"},{"key":"key-10.1145\/3184558.3186582-5","unstructured":"M. Banko, M. J. Cafarella, S. Soderland, M. Broadhead, and O. Etzioni. Open information extraction from the web. In 20th IJCAI, pages 2670--2676, 2007."},{"key":"key-10.1145\/3184558.3186582-6","doi-asserted-by":"crossref","unstructured":"L. Blanco, N. Dalvi, and A. Machanavajjhala. Highly efficient algorithms for structural clustering of large websites. In 20th WWW, pages 437--446, 2011.","DOI":"10.1145\/1963405.1963468"},{"key":"key-10.1145\/3184558.3186582-7","doi-asserted-by":"crossref","unstructured":"P. Bohannon, N. Dalvi, Y. Filmus, N. Jacoby, S. Keerthi, and A. Kirpal. Automatic web-scale information extraction. In ACM SIGMOD, pages 609--612, 2012.","DOI":"10.1145\/2213836.2213912"},{"key":"key-10.1145\/3184558.3186582-8","unstructured":"A. Z. Broder. On the resemblance and containment of documents. In Compression and Complexity of Sequences, pages 21--29, 1997."},{"key":"key-10.1145\/3184558.3186582-9","doi-asserted-by":"crossref","unstructured":"A. Z. Broder. Identifying and filtering near-duplicate documents. In 11th CPM, pages 1--10, 2000.","DOI":"10.1007\/3-540-45123-4_1"},{"key":"key-10.1145\/3184558.3186582-10","doi-asserted-by":"crossref","unstructured":"A. Z. Broder, S. C. Glassman, M. S. Manasse, and G. Zweig. Syntactic clustering of the web. Computer Networks and ISDN Systems, 29(8):1157--1166, 1997.","DOI":"10.1016\/S0169-7552(97)00031-7"},{"key":"key-10.1145\/3184558.3186582-11","doi-asserted-by":"crossref","unstructured":"M. J. Cafarella, A. Halevy, D. Z. Wang, E. Wu, and Y. Zhang. Webtables: Exploring the power of tables on the web. Proc. VLDB Endow., 1(1):538--549, 2008.","DOI":"10.14778\/1453856.1453916"},{"key":"key-10.1145\/3184558.3186582-12","doi-asserted-by":"crossref","unstructured":"C.-H. Chang, M. Kayed, M. R. Girgis, and K. F. Shaalan. A survey of web information extraction systems. IEEE Trans. on Knowl. and Data Eng., 18(10):1411--1428, Oct. 2006.","DOI":"10.1109\/TKDE.2006.152"},{"key":"key-10.1145\/3184558.3186582-13","doi-asserted-by":"crossref","unstructured":"C.-H. Chang and S.-C. Lui. Iepad: information extraction based on pattern discovery. In 10th WWW, pages 681--688, 2001.","DOI":"10.1145\/371920.372182"},{"key":"key-10.1145\/3184558.3186582-14","doi-asserted-by":"crossref","unstructured":"V. Crescenzi, P. Merialdo, and P. Missier. Clustering web pages based on their structure. Data & Knowledge Engineering, 54(3):279--299, 2005.","DOI":"10.1016\/j.datak.2004.11.004"},{"key":"key-10.1145\/3184558.3186582-15","unstructured":"A. Culotta, R. Bekkerman, and A.McCallum. Extracting social networks and contact information from email and the Web. In CEAS, 2004."},{"key":"key-10.1145\/3184558.3186582-16","doi-asserted-by":"crossref","unstructured":"N. Dalvi, P. Bohannon, and F. Sha. Robust web extraction: an approach based on a probabilistic tree-edit model. In ACM SIGMOD, pages 335--348, 2009.","DOI":"10.1145\/1559845.1559882"},{"key":"key-10.1145\/3184558.3186582-17","doi-asserted-by":"crossref","unstructured":"J. Dean and S. Ghemawat. Mapreduce: simplified data processing on large clusters. Commun. ACM, 51(1):107--113, 2008.","DOI":"10.1145\/1327452.1327492"},{"key":"key-10.1145\/3184558.3186582-18","doi-asserted-by":"crossref","unstructured":"D. Di Castro, L. Lewin-Eytan, Y. Maarek, R. Wolff, and E. Zohar. Enforcing k-anonymity in web mail auditing. In WSDM, 2016.","DOI":"10.1145\/2835776.2835803"},{"key":"key-10.1145\/3184558.3186582-19","doi-asserted-by":"crossref","unstructured":"H. Elmeleegy, J. Madhavan, and A. Halevy. Harvesting relational tables from lists on the web. The VLDB Journal, 20(2):209--226, 2011.","DOI":"10.1007\/s00778-011-0223-0"},{"key":"key-10.1145\/3184558.3186582-20","doi-asserted-by":"crossref","unstructured":"W. Gatterbauer, P. Bohunsky, M. Herzog, B. Krüpl, and B. Pollak. Towards domain-independent information extraction from web tables. In 16th WWW, pages 71--80, 2007.","DOI":"10.1145\/1242572.1242583"},{"key":"key-10.1145\/3184558.3186582-21","doi-asserted-by":"crossref","unstructured":"M. Grbovic, G. Halawi, Z. Karnin, and Y. Maarek. How many folders do you really need classifying email into a handful of categories. In CIKM, 2014.","DOI":"10.1145\/2661829.2662018"},{"key":"key-10.1145\/3184558.3186582-22","doi-asserted-by":"crossref","unstructured":"Q. Hao, R. Cai, Y. Pang, and L. Zhang. From one tree to a forest: a unified solution for structured web data extraction. In 34th ACM SIGIR, pages 775--784, 2011.","DOI":"10.1145\/2009916.2010020"},{"key":"key-10.1145\/3184558.3186582-23","doi-asserted-by":"crossref","unstructured":"M. Henzinger. Finding near-duplicate web pages: a large-scale evaluation of algorithms. In 29th ACM SIGIR, pages 284--291, 2006.","DOI":"10.1145\/1148170.1148222"},{"key":"key-10.1145\/3184558.3186582-24","doi-asserted-by":"crossref","unstructured":"T. K. Ho. Random decision forests. In Document Analysis and Recognition, 1995, volume 1, pages 278--282. IEEE, 1995.","DOI":"10.1109\/ICDAR.1995.598994"},{"key":"key-10.1145\/3184558.3186582-25","unstructured":"M. Kayed and C.-H. Chang. Fivatech: Page-level web data extraction from template pages. Knowledge and Data Engineering, IEEE Transactions on, 22(2):249--263, 2010."},{"key":"key-10.1145\/3184558.3186582-26","doi-asserted-by":"crossref","unstructured":"B. Liu, R. Grossman, and Y. Zhai. Mining data records in web pages. In 9th ACM SIGKDD, pages 601--606, 2003.","DOI":"10.1145\/956750.956826"},{"key":"key-10.1145\/3184558.3186582-27","doi-asserted-by":"crossref","unstructured":"W. Liu, X. Meng, and W. Meng. Vide: A vision-based approach for deep web data extraction. IEEE Transactions on Knowledge and Data Engineering, 22(3):447--460, 2010.","DOI":"10.1109\/TKDE.2009.109"},{"key":"key-10.1145\/3184558.3186582-28","doi-asserted-by":"crossref","unstructured":"C. D. Manning, P. Raghavan, and H. Schütze. Introduction to information retrieval, volume 1. 2008.","DOI":"10.1017\/CBO9780511809071"},{"key":"key-10.1145\/3184558.3186582-29","doi-asserted-by":"crossref","unstructured":"E. Minkov, R. C. Wang, and W. W. Cohen. Extracting personal names from email: applying named entity recognition to informal text. In HLT\/EMNLP, pages 443--450, 2005.","DOI":"10.3115\/1220575.1220631"},{"key":"key-10.1145\/3184558.3186582-30","doi-asserted-by":"crossref","unstructured":"D. Nadeau and S. Sekine. A survey of named entity recognition and classification. Lingvisticae Investigationes, 30(1):3--26, 2007.","DOI":"10.1075\/li.30.1.03nad"},{"key":"key-10.1145\/3184558.3186582-31","unstructured":"A. Nierman and H. Jagadish. Evaluating structural similarity in xml documents. In WebDB, volume 2, pages 61--66, 2002."},{"key":"key-10.1145\/3184558.3186582-32","doi-asserted-by":"crossref","unstructured":"P. Senellart, A. Mittal, D. Muschick, R. Gilleron, and M. Tommasi. Automatic wrapper induction from hidden-web sources with domain knowledge. In 10th WIDM, pages 9--16, 2008.","DOI":"10.1145\/1458502.1458505"},{"key":"key-10.1145\/3184558.3186582-33","doi-asserted-by":"crossref","unstructured":"H. A. Sleiman and R. Corchuelo. Tex: An efficient and effective unsupervised web information extractor. Knowledge-Based Systems, 39:109--123, 2013.","DOI":"10.1016\/j.knosys.2012.10.009"},{"key":"key-10.1145\/3184558.3186582-34","doi-asserted-by":"crossref","unstructured":"H. A. Sleiman and R. Corchuelo. Trinity: on using trinary trees for unsupervised web data extraction. IEEE Transactions on Knowledge and Data Engineering, 26(6):1544--1556, 2014.","DOI":"10.1109\/TKDE.2013.161"},{"key":"key-10.1145\/3184558.3186582-35","doi-asserted-by":"crossref","unstructured":"W. Thamviset and S. Wongthanavasu. Information extraction for deep web using repetitive subject pattern. World Wide Web, pages 1109--1139, 2014.","DOI":"10.1007\/s11280-013-0248-y"},{"key":"key-10.1145\/3184558.3186582-36","doi-asserted-by":"crossref","unstructured":"J. Wang and F. H. Lochovsky. Data extraction and label assignment for web databases. In 12th WWW, pages 187--196, 2003.","DOI":"10.1145\/775152.775179"},{"key":"key-10.1145\/3184558.3186582-37","doi-asserted-by":"crossref","unstructured":"J. B. Wendt, M. Bendersky, L. Garcia-Pueyo, V. Josifovski, B. Miklos, and I. Krka. Hierarchical label propagation and discovery for machine generated email. In WSDM, 2016.","DOI":"10.1145\/2835776.2835780"},{"key":"key-10.1145\/3184558.3186582-38","doi-asserted-by":"crossref","unstructured":"W. Zhang, A. Ahmed, J. Yang, V. Josifovski, and A. J. Smola. Annotating needles in the haystack without looking: Product information extraction from emails. In 21th ACM SIGKDD, pages 2257--2266, 2015.","DOI":"10.1145\/2783258.2788580"}],"event":{"name":"Companion of the The Web Conference 2018","location":"Lyon, France","acronym":"WWW '18","number":"2018","sponsor":["IW3C2, International World Wide Web Conference Committee","SIGWEB, ACM Special Interest Group on Hypertext, Hypermedia, and Web"],"start":{"date-parts":[[2018,4,23]]},"end":{"date-parts":[[2018,4,27]]}},"container-title":["Companion of the The Web Conference 2018 on The Web Conference 2018 - WWW '18"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3184558.3186582","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/dl.acm.org\/ft_gateway.cfm?id=3186582&ftid=1958242&dwn=1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,3]],"date-time":"2025-07-03T19:26:31Z","timestamp":1751570791000},"score":1,"resource":{"primary":{"URL":"http:\/\/dl.acm.org\/citation.cfm?doid=3184558.3186582"}},"subtitle":[],"proceedings-subject":"The Web Conference 2018","short-title":[],"issued":{"date-parts":[[2018]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1145\/3184558.3186582","relation":{},"subject":[],"published":{"date-parts":[[2018]]}}}