{"url":"/dataset/doc2dial-1","name":"Doc2Dial","full_name":"Doc2Dial: Document-grounded Dialogue","description_markdown":"For goal-oriented document-grounded dialogs, it often involves complex contexts for identifying the most relevant information, which requires better understanding of the inter-relations between conversations and documents. Meanwhile, many online user-oriented documents use both semi-structured and unstructured contents for guiding users to access information of different contexts. Thus, we create a new goal-oriented document-grounded dialogue dataset that captures more diverse scenarios derived from various document contents from multiple domains such ssa.gov and studentaid.gov. For data collection, we propose a novel pipeline approach for dialogue data construction, which has been adapted and evaluated for several domains.","description_withheld":null,"homepage":"https://doc2dial.github.io","introduced_date":"2020-11-12","introduced_date_note":null,"introduced_by":{"paper":"/paper/doc2dial-a-goal-oriented-document-grounded","title":"doc2dial: A Goal-Oriented Document-Grounded Dialogue Dataset","first_author":"Song Feng","url":null},"license":{"name":"Apache-2.0 License","url":null},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Question Answering","url":"/task/question-answering","datasets_with_task":"/datasets/task/question-answering"},{"name":"Dialogue Understanding","url":"/task/dialogue-understanding","datasets_with_task":"/datasets/task/dialogue-understanding"},{"name":"Dialogue Generation","url":"/task/dialogue-generation","datasets_with_task":"/datasets/task/dialogue-generation"},{"name":"Dialogue Act Classification","url":"/task/dialogue-act-classification","datasets_with_task":"/datasets/task/dialogue-act-classification"},{"name":"Goal-Oriented Dialog","url":"/task/goal-oriented-dialog","datasets_with_task":"/datasets/task/goal-oriented-dialog"},{"name":"Conversational Question Answering","url":"/task/conversational-question-answering","datasets_with_task":"/datasets/task/conversational-question-answering"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["Doc2Dial"],"data_loaders":[],"num_papers_in_archive":36,"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."}