{"url":"/dataset/pgdataset","name":"PGDataset","full_name":"Profile Generation Dataset","description_markdown":"PGDataset (Profile Generation Dataset) is a dataset created for the PGTask (Profile Generation Task), where the goal is to extract/generate a profile sentence given a dialogue utterance.","description_withheld":null,"homepage":"https://github.com/ruinunca/PGTask/","introduced_date":"2023-04-13","introduced_date_note":null,"introduced_by":{"paper":"/paper/pgtask-introducing-the-task-of-profile","title":"PGTask: Introducing the Task of Profile Generation from Dialogues","first_author":"Rui Ribeiro","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"},{"name":"Dialog","url":"/datasets/modality/dialog"}],"tasks":[{"name":"Profile Generation","url":"/task/pgtask","datasets_with_task":"/datasets/task/pgtask"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["PGDataset"],"data_loaders":[],"num_papers_in_archive":1,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/pgtask-on-pgdataset","task":"Profile Generation","dataset_variant":"PGDataset","rows":2,"metrics":["BLEU-1","BLEU-2","BLEU-3","BLEU-4","BertScore","ROUGE-1","ROUGE-2","ROUGE-L"],"first_row_in_archive_order":{"model":"gpt2-small","paper":"/paper/pgtask-introducing-the-task-of-profile","metrics":{"BLEU-1":"61.30","BLEU-2":"32.3","BLEU-3":"20.62","BLEU-4":"9.44","BertScore":"94.39","ROUGE-1":"50.07","ROUGE-2":"28.31","ROUGE-L":"50.00"},"code_links":[{"title":"ruinunca/PGTask","url":"https://github.com/ruinunca/PGTask"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/pgtask-introducing-the-task-of-profile","title":"PGTask: Introducing the Task of Profile Generation from Dialogues","date":"2023-04-13","rows_on_this_dataset":2,"code_links":1,"syntology":null}],"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."}