{"url":"/dataset/personaldialog","name":"PersonalDialog","full_name":null,"description_markdown":"PersonalDialog is a large-scale multi-turn dialogue dataset containing various traits from a large number of speakers. The dataset consists of 20.83M sessions and 56.25M utterances from 8.47M speakers. Each utterance is associated with a speaker who is marked with traits like Age, Gender, Location, Interest Tags, etc. Several anonymization schemes are designed to protect the privacy of each speaker. \r\n\r\nSource: [Personalized Dialogue Generation with Diversified Traits](https://arxiv.org/abs/1901.09672)\r\nImage Source: [https://arxiv.org/pdf/1901.09672v2.pdf](https://arxiv.org/pdf/1901.09672v2.pdf)","description_withheld":null,"homepage":"https://github.com/silverriver/PersonalDilaog","introduced_date":"2019-01-28","introduced_date_note":null,"introduced_by":{"paper":"/paper/personalized-dialogue-generation-with","title":"Personalized Dialogue Generation with Diversified Traits","first_author":"Yinhe Zheng","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Text Generation","url":"/task/text-generation","datasets_with_task":"/datasets/task/text-generation"},{"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":[{"name":"Chinese","url":"/datasets/language/chinese"}],"variants":["PersonalDialog"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/silver/personal_dialog","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/silverriver/PersonalDilaog","url":"https://github.com/silverriver/PersonalDilaog","frameworks":[]}],"num_papers_in_archive":13,"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."}