{"url":"/dataset/lecturebank","name":"LectureBank","full_name":null,"description_markdown":"**LectureBank** Dataset is a manually collected dataset of lecture slides. It contains 1,352 online lecture files from 60 courses covering 5 different domains, including Natural Language Processing (nlp), Machine Learning (ml), Artificial Intelligence (ai), Deep Learning (dl) and Information Retrieval (ir). In addition, it also contains the corresponding annotations for each slide.\n\nSource: [https://github.com/Yale-LILY/LectureBank](https://github.com/Yale-LILY/LectureBank)\nImage Source: [https://github.com/Yale-LILY/LectureBank](https://github.com/Yale-LILY/LectureBank)","description_withheld":null,"homepage":"https://github.com/Yale-LILY/LectureBank","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/what-should-i-learn-first-introducing","title":"What Should I Learn First: Introducing LectureBank for NLP Education and Prerequisite Chain Learning","first_author":"Irene Li","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["LectureBank"],"data_loaders":[{"repo":"https://github.com/Yale-LILY/LectureBank","url":"https://github.com/Yale-LILY/LectureBank","frameworks":[]}],"num_papers_in_archive":10,"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."}