{"url":"/dataset/bwb","name":"BWB","full_name":null,"description_markdown":"The **BWB** corpus consists of Chinese novels translated by experts into English, and the annotated test set is designed to probe the ability of machine translation systems to model various discourse phenomena.\r\n\r\nSource: [A Bilingual Parallel Corpus with Discourse Annotations](https://arxiv.org/pdf/2210.14667v1.pdf)\r\n\r\nImage Source: [https://arxiv.org/pdf/2210.14667v1.pdf](https://arxiv.org/pdf/2210.14667v1.pdf)","description_withheld":null,"homepage":"https://github.com/EleanorJiang/BlonDe/tree/main/BWB","introduced_date":"2022-10-26","introduced_date_note":null,"introduced_by":{"paper":"/paper/a-bilingual-parallel-corpus-with-discourse","title":"A Bilingual Parallel Corpus with Discourse Annotations","first_author":"Yuchen Eleanor Jiang","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Machine Translation","url":"/task/machine-translation","datasets_with_task":"/datasets/task/machine-translation"},{"name":"Translation","url":"/task/translation","datasets_with_task":"/datasets/task/translation"},{"name":"Document Level Machine Translation","url":"/task/document-level-machine-translation","datasets_with_task":"/datasets/task/document-level-machine-translation"}],"languages":[{"name":"English","url":"/datasets/language/english"},{"name":"Chinese","url":"/datasets/language/chinese"}],"variants":["BWB"],"data_loaders":[],"num_papers_in_archive":1,"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."}