{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T19:39:31Z","timestamp":1771616371434,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":12,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,4,30]],"date-time":"2023-04-30T00:00:00Z","timestamp":1682812800000},"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":[[2023,4,30]]},"DOI":"10.1145\/3543873.3587331","type":"proceedings-article","created":{"date-parts":[[2023,4,28]],"date-time":"2023-04-28T11:36:14Z","timestamp":1682681774000},"page":"136-139","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["The Web Data Commons Schema.org Data Set Series"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9379-2048","authenticated-orcid":false,"given":"Alexander","family":"Brinkmann","sequence":"first","affiliation":[{"name":"University of Mannheim, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1783-2482","authenticated-orcid":false,"given":"Anna","family":"Primpeli","sequence":"additional","affiliation":[{"name":"University of Mannheim, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2367-0237","authenticated-orcid":false,"given":"Christian","family":"Bizer","sequence":"additional","affiliation":[{"name":"University of Mannheim, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,4,30]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Proceedings of the 20th International Semantic Web Conference. 338\u2013356","author":"Alrashed Tarfah","unstructured":"Tarfah Alrashed, Dimitris Paparas, Omar Benjelloun, and al.2021. Dataset or Not? A study on the veracity of semantic markup for dataset pages. In Proceedings of the 20th International Semantic Web Conference. 338\u2013356."},{"key":"e_1_3_2_1_2_1","volume-title":"Improving Hierarchical Product Classification using Domain-specific Language Modelling. Bulletin of the IEEE Computer Society Technical Committee on Data Engineering","author":"Brinkmann Alexander","year":"2021","unstructured":"Alexander Brinkmann and Christian Bizer. 2021. Improving Hierarchical Product Classification using Domain-specific Language Modelling. Bulletin of the IEEE Computer Society Technical Committee on Data Engineering (2021), 14\u201325."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/2766462.2767739"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/2844544"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-93417-4_22"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/2797115.2797124"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-11964-9_18"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-27729-5_7"},{"key":"e_1_3_2_1_9_1","volume-title":"Proceedings of the Linked Data Workshop (LDOW) at the International World Wide Web Conference.","author":"Mika Peter","year":"2012","unstructured":"Peter Mika and Tim Potter. 2012. Metadata Statistics for a Large Web Corpus. In Proceedings of the Linked Data Workshop (LDOW) at the International World Wide Web Conference."},{"key":"e_1_3_2_1_10_1","volume-title":"The WDC Training Dataset and Gold Standard for Large-Scale Product Matching. In Companion Proceedings of The 2019 World Wide Web Conference. 381\u2013386","author":"Primpeli Anna","year":"2019","unstructured":"Anna Primpeli, Ralph Peeters, and Christian Bizer. 2019. The WDC Training Dataset and Gold Standard for Large-Scale Product Matching. In Companion Proceedings of The 2019 World Wide Web Conference. 381\u2013386."},{"key":"e_1_3_2_1_11_1","unstructured":"Christoph Schuhmann Romain Beaumont Richard Vencu and al.2022. LAION-5B: An open large-scale dataset for training next generation image-text models. arXiv:2210.08402 [cs]."},{"key":"e_1_3_2_1_12_1","volume-title":"7th Workshop on the Challenges in the Management of Large Corpora. 9\u201316","author":"Javier\u00a0Ortiz Su\u00e1rez Pedro","year":"2019","unstructured":"Pedro Javier\u00a0Ortiz Su\u00e1rez, Beno\u00eet Sagot, and Laurent Romary. 2019. Asynchronous pipelines for processing huge corpora on medium to low resource infrastructures. In 7th Workshop on the Challenges in the Management of Large Corpora. 9\u201316."}],"event":{"name":"WWW '23: The ACM Web Conference 2023","location":"Austin TX USA","acronym":"WWW '23","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Companion Proceedings of the ACM Web Conference 2023"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3543873.3587331","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3543873.3587331","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T23:37:21Z","timestamp":1755819441000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3543873.3587331"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,30]]},"references-count":12,"alternative-id":["10.1145\/3543873.3587331","10.1145\/3543873"],"URL":"https:\/\/doi.org\/10.1145\/3543873.3587331","relation":{},"subject":[],"published":{"date-parts":[[2023,4,30]]},"assertion":[{"value":"2023-04-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}