{"url":"/dataset/cmu-dog","name":"CMU DoG","full_name":"CMU Document Grounded Conversations Dataset","description_markdown":"This is a document grounded dataset for text conversations. \"Document Grounded Conversations\" are conversations that are about the contents of a specified document. In this dataset the specified documents are Wikipedia articles about popular movies. The dataset contains 4112 conversations with an average of 21.43 turns per conversation.\r\n\r\nSource: [https://github.com/festvox/datasets-CMU_DoG](https://github.com/festvox/datasets-CMU_DoG)\r\nImage Source: [https://arxiv.org/pdf/1809.07358v1.pdf](https://arxiv.org/pdf/1809.07358v1.pdf)","description_withheld":null,"homepage":"https://github.com/festvox/datasets-CMU_DoG","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/a-dataset-for-document-grounded-conversations","title":"A Dataset for Document Grounded Conversations","first_author":"Kangyan Zhou","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Domain Adaptation","url":"/task/domain-adaptation","datasets_with_task":"/datasets/task/domain-adaptation"},{"name":"Language Modelling","url":"/task/language-modelling","datasets_with_task":"/datasets/task/language-modelling"},{"name":"Dialogue Generation","url":"/task/dialogue-generation","datasets_with_task":"/datasets/task/dialogue-generation"}],"languages":[],"variants":["CMU DoG"],"data_loaders":[{"repo":"https://github.com/facebookresearch/ParlAI","url":"https://parl.ai/docs/tasks.html#cmu-document-grounded-conversations","frameworks":["pytorch"]},{"repo":"https://github.com/festvox/datasets-CMU_DoG","url":"https://github.com/festvox/datasets-CMU_DoG","frameworks":[]}],"num_papers_in_archive":15,"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":"2026-09-25T09:33:49+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."}