{"url":"/dataset/usr-topicalchat","name":"USR-TopicalChat","full_name":null,"description_markdown":"This dataset was collected with the goal of assessing dialog evaluation metrics. In the paper, USR: An Unsupervised and Reference Free Evaluation Metric for Dialog (Mehri and Eskenazi, 2020), the authors collect this data to measure the quality of several existing word-overlap and embedding-based metrics, as well as their newly proposed USR metric.","description_withheld":null,"homepage":"http://shikib.com/usr","introduced_date":"2020-05-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/usr-an-unsupervised-and-reference-free","title":"USR: An Unsupervised and Reference Free Evaluation Metric for Dialog Generation","first_author":"Shikib Mehri","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Dialogue Evaluation","url":"/task/dialogue-evaluation","datasets_with_task":"/datasets/task/dialogue-evaluation"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["USR-TopicalChat"],"data_loaders":[],"num_papers_in_archive":7,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/dialogue-evaluation-on-usr-topicalchat","task":"Dialogue Evaluation","dataset_variant":"USR-TopicalChat","rows":6,"metrics":["Spearman Correlation","Pearson Correlation"],"first_row_in_archive_order":{"model":"MDD-Eval","paper":"/paper/mdd-eval-self-training-on-augmented-data-for","metrics":{"Pearson Correlation":"0.4575","Spearman Correlation":"0.5109"},"code_links":[{"title":"e0397123/mdd-eval","url":"https://github.com/e0397123/mdd-eval"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/mdd-eval-self-training-on-augmented-data-for","title":"MDD-Eval: Self-Training on Augmented Data for Multi-Domain Dialogue Evaluation","date":"2021-12-14","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/proxy-indicators-for-the-quality-of-open","title":"Proxy Indicators for the Quality of Open-domain Dialogues","date":"2021-11-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/usr-an-unsupervised-and-reference-free","title":"USR: An Unsupervised and Reference Free Evaluation Metric for Dialog Generation","date":"2020-05-01","rows_on_this_dataset":4,"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."}