{"url":"/dataset/trec-10","name":"TREC-10","full_name":"TREC-10 Question Classification","description_markdown":"A question type classification dataset with 6 classes for questions about a person, location, numeric information, etc. The test split has 500 questions, and the training split has 5452 questions.\r\n\r\nPaper: [Learning Question Classifiers](https://www.aclweb.org/anthology/C02-1150/)","description_withheld":null,"homepage":"https://cogcomp.seas.upenn.edu/Data/QA/QC/","introduced_date":"2002-08-01","introduced_date_note":null,"introduced_by":null,"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Text Classification","url":"/task/text-classification","datasets_with_task":"/datasets/task/text-classification"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["TREC-10","trec"],"data_loaders":[{"repo":"https://github.com/tensorflow/datasets","url":"https://www.tensorflow.org/datasets/catalog/trec","frameworks":["tf","jax"]}],"num_papers_in_archive":6,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/text-classification-on-trec-10","task":"Text Classification","dataset_variant":"TREC-10","rows":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"BERT","paper":"/paper/transformers-are-short-text-classifiers-a","metrics":{"Accuracy":"99.40"},"code_links":[{"title":"FKarl/short-text-classification","url":"https://github.com/FKarl/short-text-classification"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/transformers-are-short-text-classifiers-a","title":"Transformers are Short Text Classifiers: A Study of Inductive Short Text Classifiers on Benchmarks and Real-world Datasets","date":"2022-11-30","rows_on_this_dataset":1,"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."}