{"url":"/dataset/perseus","name":"Perseus","full_name":null,"description_markdown":"**Perseus** is a dataset for Cross-Lingual Summarization (CLS) which collects about 94K Chinese scientific documents paired with English summaries. The average length of documents in Perseus is more than two thousand tokens.\r\n\r\nSource: [Long-Document Cross-Lingual Summarization](https://arxiv.org/pdf/2212.00586v1.pdf)\r\n\r\nImage Source: [https://arxiv.org/pdf/2212.00586v1.pdf](https://arxiv.org/pdf/2212.00586v1.pdf)","description_withheld":null,"homepage":"https://github.com/LearnItBoy/Perseus","introduced_date":"2022-12-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/long-document-cross-lingual-summarization","title":"Long-Document Cross-Lingual Summarization","first_author":"Shaohui Zheng","url":null},"license":null,"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"tasks":[{"name":"Machine Translation","url":"/task/machine-translation","datasets_with_task":"/datasets/task/machine-translation"}],"languages":[{"name":"English","url":"/datasets/language/english"},{"name":"Chinese","url":"/datasets/language/chinese"}],"variants":["Perseus"],"data_loaders":[],"num_papers_in_archive":2,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"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."}