{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/a-publicly-available-annotated-corpus-for","title":"A Publicly Available Annotated Corpus for Supervised Email Summarization","arxiv_id":null,"date":"2008-07-13","proceeding":"AAAI 2008 7","authors":["Jan Ulrich","Gabriel Murray","Giuseppe Carenini"],"abstract":"Annotated email corpora are necessary for evaluation and training of machine learning summarization techniques. The scarcity of corpora has been a limiting factor for research in this field. We describe our process of creating a new annotated email thread corpus that will be made publicly available. We present the trade-offs of the different annotation methods that could be used.","url_abs":"https://aaai.org/papers/ws08-04-014-a-publicly-available-annotated-corpus-for-supervised-email-summarization/","url_pdf":"https://cdn.aaai.org/Workshops/2008/WS-08-04/WS08-04-014.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[],"methods":[],"datasets_introduced":[{"slug":"bc3-email-corpus","name":"BC3 email corpus","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}