{"url":"/dataset/mlb-dataset","name":"MLB Dataset","full_name":null,"description_markdown":"A new dataset on the baseball domain.\r\n\r\nSource: [Data-to-text Generation with Entity Modeling](/paper/data-to-text-generation-with-entity-modeling)","description_withheld":null,"homepage":"https://github.com/ratishsp/mlb-data-scripts","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/data-to-text-generation-with-entity-modeling","title":"Data-to-text Generation with Entity Modeling","first_author":"Ratish Puduppully","url":null},"license":null,"modalities":[],"tasks":[{"name":"Text Generation","url":"/task/text-generation","datasets_with_task":"/datasets/task/text-generation"},{"name":"Data-to-Text Generation","url":"/task/data-to-text-generation","datasets_with_task":"/datasets/task/data-to-text-generation"}],"languages":[],"variants":["MLB Dataset"],"data_loaders":[{"repo":"https://github.com/ratishsp/mlb-data-scripts","url":"https://github.com/ratishsp/mlb-data-scripts","frameworks":[]}],"num_papers_in_archive":5,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/data-to-text-generation-on-mlb-dataset-2","task":"Data-to-Text Generation","dataset_variant":"MLB Dataset","rows":4,"metrics":["BLEU"],"first_row_in_archive_order":{"model":"SeqPlan","paper":"/paper/data-to-text-generation-with-variational","metrics":{"BLEU":"14.29"},"code_links":[{"title":"ratishsp/data2text-seq-plan-py","url":"https://github.com/ratishsp/data2text-seq-plan-py"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/data-to-text-generation-with-variational","title":"Data-to-text Generation with Variational Sequential Planning","date":"2022-02-28","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/may-the-force-be-with-your-copy-mechanism-1","title":"May the Force Be with Your Copy Mechanism: Enhanced Supervised-Copy Method for Natural Language Generation","date":"2021-12-20","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/data-to-text-generation-with-macro-planning","title":"Data-to-text Generation with Macro Planning","date":"2021-02-04","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/data-to-text-generation-with-entity-modeling","title":"Data-to-text Generation with Entity Modeling","date":"2019-06-07","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":1,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":1,"samples_harvested":2,"samples_ran":1,"samples_unverified":1,"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."}