{"url":"/dataset/delemon","name":"DuLeMon","full_name":"Baidu Long-term Memory Conversation","description_markdown":"DuLeMon is a large-scale Chinese Long-term Memory Conversation dataset, which simulates long-term memory conversations and focuses on the ability to actively construct and utilize the user's and the bot's persona in a long-term interaction. DuLeMon contains about 27.5k human-human conversations, 449k utterances, and 12k persona grounding sentences. This corpus can be used to explore Long-term Memory Conversation, Personalized Dialogue, and Persona Extraction / Matching / Retrieval.","description_withheld":null,"homepage":"https://github.com/PaddlePaddle/Research/tree/master/NLP/ACL2022-DuLeMon","introduced_date":"2022-03-11","introduced_date_note":null,"introduced_by":{"paper":"/paper/long-time-no-see-open-domain-conversation","title":"Long Time No See! Open-Domain Conversation with Long-Term Persona Memory","first_author":"Xinchao Xu","url":null},"license":{"name":"MIT","url":null},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Open-Domain Dialog","url":"/task/open-domain-dialog","datasets_with_task":"/datasets/task/open-domain-dialog"},{"name":"Conversational Response Generation","url":"/task/conversational-response-generation","datasets_with_task":"/datasets/task/conversational-response-generation"},{"name":"Text Matching","url":"/task/text-matching","datasets_with_task":"/datasets/task/text-matching"}],"languages":[{"name":"Chinese","url":"/datasets/language/chinese"}],"variants":["DuLeMon"],"data_loaders":[],"num_papers_in_archive":14,"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."}