{"url":"/dataset/cornell-movie-dialogs-corpus","name":"Cornell Movie-Dialogs Corpus","full_name":null,"description_markdown":"This corpus contains a large metadata-rich collection of fictional conversations extracted from raw movie scripts:\r\n\r\n- 220,579 conversational exchanges between 10,292 pairs of movie characters\r\n- involves 9,035 characters from 617 movies\r\n- in total 304,713 utterances\r\n- movie metadata included:\r\n    - genres\r\n    - release year\r\n    - IMDB rating\r\n    - number of IMDB votes\r\n    - IMDB rating\r\n- character metadata included:\r\n    - gender (for 3,774 characters)\r\n    - position on movie credits (3,321 characters)\r\n\r\nSource: [Cornell Movie-Dialogs Corpus](http://www.cs.cornell.edu/~cristian/Cornell_Movie-Dialogs_Corpus.html)","description_withheld":null,"homepage":"http://www.cs.cornell.edu/~cristian/Cornell_Movie-Dialogs_Corpus.html","introduced_date":null,"introduced_date_note":null,"introduced_by":null,"license":null,"modalities":[],"tasks":[],"languages":[],"variants":["Cornell Movie-Dialogs Corpus"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/cornell-movie-dialog/cornell_movie_dialog","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/cornell_movie_dialog","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/facebookresearch/ParlAI","url":"https://parl.ai/docs/tasks.html#cornell-movie","frameworks":["pytorch"]}],"num_papers_in_archive":0,"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."}