{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T15:57:17Z","timestamp":1783439837660,"version":"3.54.6"},"publisher-location":"New York, NY, USA","reference-count":11,"publisher":"ACM","license":[{"start":{"date-parts":[[2018,7,19]],"date-time":"2018-07-19T00:00:00Z","timestamp":1531958400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Swiss National Science Foundation","award":["NCCR MARVEL"],"award-info":[{"award-number":["NCCR MARVEL"]}]},{"name":"Horizon 2020 NMBP-23-2016","award":["Force project 721027"],"award-info":[{"award-number":["Force project 721027"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2018,7,19]]},"DOI":"10.1145\/3219819.3219834","type":"proceedings-article","created":{"date-parts":[[2018,7,19]],"date-time":"2018-07-19T13:05:12Z","timestamp":1532005512000},"page":"774-782","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":40,"title":["Corpus Conversion Service"],"prefix":"10.1145","author":[{"given":"Peter W J","family":"Staar","sequence":"first","affiliation":[{"name":"IBM Research, Zurich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michele","family":"Dolfi","sequence":"additional","affiliation":[{"name":"IBM Research, Zurich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christoph","family":"Auer","sequence":"additional","affiliation":[{"name":"IBM Research, Zurich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Costas","family":"Bekas","sequence":"additional","affiliation":[{"name":"IBM Research, Zurich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2018,7,19]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2015.7333941"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1010933404324"},{"key":"e_1_3_2_2_3_1","unstructured":"R. Cattoni T. Coianiz S. Messelodi and C. M. Modena. 1998. Geometric layout analysis techniques for document image understanding: a review. Technical Report.  R. Cattoni T. Coianiz S. Messelodi and C. M. Modena. 1998. Geometric layout analysis techniques for document image understanding: a review. Technical Report."},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/11551362_9"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"e_1_3_2_2_7_1","volume-title":"Berg","author":"Liu Wei","year":"2016"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"e_1_3_2_2_9_1","volume-title":"Faster, Stronger. arXiv preprint arXiv:1612.08242","author":"Redmon Joseph","year":"2016"},{"key":"e_1_3_2_2_10_1","volume-title":"Advances in Neural Information Processing Systems 28","author":"Ren Shaoqing"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"crossref","unstructured":"Peter W J Staar Michele Dolfi Christoph Auer and Costas Bekas. 2018. Corpus Conversion Service poster at the SysML conference. http:\/\/www.sysml.cc\/doc\/76.pdf  Peter W J Staar Michele Dolfi Christoph Auer and Costas Bekas. 2018. Corpus Conversion Service poster at the SysML conference. http:\/\/www.sysml.cc\/doc\/76.pdf","DOI":"10.1145\/3219819.3219834"}],"event":{"name":"KDD '18: The 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","location":"London United Kingdom","acronym":"KDD '18","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3219819.3219834","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3219819.3219834","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T01:08:43Z","timestamp":1750208923000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3219819.3219834"}},"subtitle":["A Machine Learning Platform to Ingest Documents at Scale"],"short-title":[],"issued":{"date-parts":[[2018,7,19]]},"references-count":11,"alternative-id":["10.1145\/3219819.3219834","10.1145\/3219819"],"URL":"https:\/\/doi.org\/10.1145\/3219819.3219834","relation":{},"subject":[],"published":{"date-parts":[[2018,7,19]]},"assertion":[{"value":"2018-07-19","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}