{"url":"/dataset/bipar","name":"BiPaR","full_name":"BiPaR","description_markdown":"**BiPaR** is a manually annotated bilingual parallel novel-style machine reading comprehension (MRC) dataset, developed to support monolingual, multilingual and cross-lingual reading comprehension on novels. The biggest difference between BiPaR and existing reading comprehension datasets is that each triple (Passage, Question, Answer) in BiPaR is written in parallel in two languages. BiPaR is diverse in prefixes of questions, answer types and relationships between questions and passages. Answering the questions requires reading comprehension skills of coreference resolution, multi-sentence reasoning, and understanding of implicit causality.\r\n\r\nSource: [BiPaR](https://multinlp.github.io/BiPaR/)","description_withheld":null,"homepage":"https://multinlp.github.io/BiPaR/","introduced_date":"2019-10-11","introduced_date_note":null,"introduced_by":{"paper":"/paper/bipar-a-bilingual-parallel-dataset-for","title":"BiPaR: A Bilingual Parallel Dataset for Multilingual and Cross-lingual Reading Comprehension on Novels","first_author":"Yimin Jing","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Reading Comprehension","url":"/task/reading-comprehension","datasets_with_task":"/datasets/task/reading-comprehension"},{"name":"Coreference Resolution","url":"/task/coreference-resolution","datasets_with_task":"/datasets/task/coreference-resolution"},{"name":"Machine Reading Comprehension","url":"/task/machine-reading-comprehension","datasets_with_task":"/datasets/task/machine-reading-comprehension"}],"languages":[{"name":"English","url":"/datasets/language/english"},{"name":"Chinese","url":"/datasets/language/chinese"},{"name":"Mandarin Chinese","url":"/datasets/language/mandarin-chinese"}],"variants":["BiPaR"],"data_loaders":[],"num_papers_in_archive":6,"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."}