{"url":"/dataset/emailsum","name":"EmailSum","full_name":"Email Thread Summarization","description_markdown":"Email Thread Summarization (EmailSum) is a dataset which contains human-annotated short (<30 words) and long (<100 words) summaries of 2,549 email threads (each containing 3 to 10 emails) over a wide variety of topics. It was developed to spur research in thread summarization.\r\n\r\nSource: [EMAILSUM: Abstractive Email Thread Summarization](https://arxiv.org/pdf/2107.14691v1.pdf)\r\n\r\nImage source: [EMAILSUM: Abstractive Email Thread Summarization](https://arxiv.org/pdf/2107.14691v1.pdf)","description_withheld":null,"homepage":"https://github.com/ZhangShiyue/EmailSum","introduced_date":"2021-07-30","introduced_date_note":null,"introduced_by":{"paper":"/paper/emailsum-abstractive-email-thread","title":"EmailSum: Abstractive Email Thread Summarization","first_author":"Shiyue Zhang","url":null},"license":{"name":"None","url":null},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Email Thread Summarization","url":"/task/email-thread-summarization","datasets_with_task":"/datasets/task/email-thread-summarization"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["EmailSum","EmailSum (short)","EmailSum (long)"],"data_loaders":[{"repo":"https://github.com/ZhangShiyue/EmailSum","url":"https://github.com/ZhangShiyue/EmailSum","frameworks":[]}],"num_papers_in_archive":3,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/email-thread-summarization-on-emailsum-long","task":"Email Thread Summarization","dataset_variant":"EmailSum (long)","rows":3,"metrics":["BertS","RLsum","ROUGE-1","ROUGE-2","ROUGE-L"],"first_row_in_archive_order":{"model":"SemiSuptogether","paper":"/paper/emailsum-abstractive-email-thread","metrics":{"BertS":"32.3","RLsum":"40.67","ROUGE-1":"44.08","ROUGE-2":"14.06","ROUGE-L":"31.17"},"code_links":[{"title":"ZhangShiyue/EmailSum","url":"https://github.com/ZhangShiyue/EmailSum"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/email-thread-summarization-on-emailsum-short","task":"Email Thread Summarization","dataset_variant":"EmailSum (short)","rows":3,"metrics":["BertS","RLsum","ROUGE-1","ROUGE-2","ROUGE-L"],"first_row_in_archive_order":{"model":"SemiSuptogether","paper":"/paper/emailsum-abstractive-email-thread","metrics":{"BertS":"33.91","RLsum":"33.7","ROUGE-1":"36.98","ROUGE-2":"11.21","ROUGE-L":"28.76"},"code_links":[{"title":"ZhangShiyue/EmailSum","url":"https://github.com/ZhangShiyue/EmailSum"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/emailsum-abstractive-email-thread","title":"EmailSum: Abstractive Email Thread Summarization","date":"2021-07-30","rows_on_this_dataset":6,"code_links":1,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}