{"url":"/dataset/mmconv","name":"MMConv","full_name":null,"description_markdown":"The main goal of the data collection is to acquire highly natural conversations that cover a wide variety of styles and scenarios. In total, the presented corpus consists of five domains: Food, Hotel, Nightlife, Shopping mall and Sightseeing. Controlled by our various task settings, the collected dialogues cover between one to four domains per dialogue, and are thus of greatly varying length and complexity. There are 808 single-task dialogues that contains a single venue target and 4, 298 multi-task dialogues consisting of at least two to four venue targets. These different venues vary in domains most of the times.","description_withheld":null,"homepage":"https://github.com/lizi-git/MMConv","introduced_date":"2021-07-11","introduced_date_note":null,"introduced_by":{"paper":"/paper/mconv-an-environment-for-multimodal","title":"MConv: An Environment for Multimodal Conversational Search across Multiple Domains","first_author":"Lizi Liao","url":null},"license":{"name":"https://github.com/lizi-git/MMConv","url":"https://github.com/lizi-git/MMConv"},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Dialogue State Tracking","url":"/task/dialogue-state-tracking","datasets_with_task":"/datasets/task/dialogue-state-tracking"},{"name":"Response Generation","url":"/task/response-generation","datasets_with_task":"/datasets/task/response-generation"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["MMConv"],"data_loaders":[],"num_papers_in_archive":3,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/dialogue-state-tracking-on-mmconv","task":"Dialogue State Tracking","dataset_variant":"MMConv","rows":2,"metrics":["Categorical Accuracy","Non-Categorical Accuracy","Overall"],"first_row_in_archive_order":{"model":"PaCE","paper":"/paper/pace-unified-multi-modal-dialogue-pre","metrics":{"Categorical Accuracy":"92.2","Non-Categorical Accuracy":"43.4","Overall":"39.2"},"code_links":[{"title":"AlibabaResearch/DAMO-ConvAI","url":"https://github.com/AlibabaResearch/DAMO-ConvAI/tree/main/pace"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/response-generation-on-mmconv","task":"Response Generation","dataset_variant":"MMConv","rows":2,"metrics":["BLEU","Comb.","Inform","Success"],"first_row_in_archive_order":{"model":"PaCE","paper":"/paper/pace-unified-multi-modal-dialogue-pre","metrics":{"BLEU":"22","Comb.":"44.7","Inform":"34.5","Success":"13.9"},"code_links":[{"title":"AlibabaResearch/DAMO-ConvAI","url":"https://github.com/AlibabaResearch/DAMO-ConvAI/tree/main/pace"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/pace-unified-multi-modal-dialogue-pre","title":"PaCE: Unified Multi-modal Dialogue Pre-training with Progressive and Compositional Experts","date":"2023-05-24","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":0,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/mconv-an-environment-for-multimodal","title":"MConv: An Environment for Multimodal Conversational Search across Multiple Domains","date":"2021-07-11","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/a-simple-language-model-for-task-oriented","title":"A Simple Language Model for Task-Oriented Dialogue","date":"2020-05-02","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":14,"samples_ran":3,"samples_unverified":11,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":2,"samples_harvested":15,"samples_ran":3,"samples_unverified":12,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":1,"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."}