{"url":"/dataset/icconv","name":"ICConv","full_name":"A Large-scale Automated Intent-oriented and Context-aware Conversational Search Dataset","description_markdown":"The dataset contains 105,811 information-seeking conversations converted from MS MARCO. This dataset is constructed to relieve the data scarcity problem of conversational search to an extent. Considering the multi-intent problem and contextual information, this large-scale intent-oriented and context-aware dataset is automatically constructed based on the web search session data in MS MARCO. This dataset can be used to train and evaluate conversational search systems.","description_withheld":null,"homepage":"https://github.com/hongjx175/ICConv","introduced_date":null,"introduced_date_note":null,"introduced_by":null,"license":{"name":"CC-BY-SA 4.0","url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Conversational Search","url":"/task/conversational-search","datasets_with_task":"/datasets/task/conversational-search"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["ICConv"],"data_loaders":[],"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."}