{"url":"/dataset/mlquestions","name":"MLQuestions","full_name":null,"description_markdown":"**MLQuestions** is a domain-adaptation dataset for the machine learning domain containing 50K unaligned passages and 35K unaligned questions, and 3K aligned passage and question pairs.","description_withheld":null,"homepage":"https://github.com/McGill-NLP/MLQuestions","introduced_date":"2021-04-18","introduced_date_note":null,"introduced_by":{"paper":"/paper/back-training-excels-self-training-at","title":"Back-Training excels Self-Training at Unsupervised Domain Adaptation of Question Generation and Passage Retrieval","first_author":"Devang Kulshreshtha","url":null},"license":{"name":"Unknown","url":null},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Question Answering","url":"/task/question-answering","datasets_with_task":"/datasets/task/question-answering"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["MLQuestions"],"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."}