{"url":"/dataset/rotowire","name":"RotoWire","full_name":"RotoWire","description_markdown":"This dataset consists of (human-written) NBA basketball game summaries aligned with their corresponding box- and line-scores. Summaries taken from rotowire.com are referred to as the \"rotowire\" data.  There are 4853 distinct rotowire summaries, covering NBA games played between 1/1/2014 and 3/29/2017; some games have multiple summaries. The summaries have been randomly split into training, validation, and test sets consisting of 3398, 727, and 728 summaries, respectively.\r\n\r\nSource: [Challenges in Data-to-Document Generation](https://arxiv.org/abs/1707.08052)\r\nImage Source: [https://arxiv.org/pdf/1707.08052v1.pdf](https://arxiv.org/pdf/1707.08052v1.pdf)","description_withheld":null,"homepage":"https://github.com/harvardnlp/boxscore-data","introduced_date":"2017-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/challenges-in-data-to-document-generation","title":"Challenges in Data-to-Document Generation","first_author":"Sam Wiseman","url":null},"license":{"name":"Unknown","url":null},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Data-to-Text Generation","url":"/task/data-to-text-generation","datasets_with_task":"/datasets/task/data-to-text-generation"},{"name":"Table-to-Text Generation","url":"/task/table-to-text-generation","datasets_with_task":"/datasets/task/table-to-text-generation"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["RotoWire (Relation Generation)","Rotowire (Content Selection)","RotoWire (Content Ordering)","RotoWire"],"data_loaders":[{"repo":"https://github.com/harvardnlp/boxscore-data","url":"https://github.com/harvardnlp/boxscore-data","frameworks":[]}],"num_papers_in_archive":65,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/data-to-text-generation-on-rotowire","task":"Data-to-Text Generation","dataset_variant":"RotoWire","rows":6,"metrics":["BLEU"],"first_row_in_archive_order":{"model":"HierarchicalEncoder + NR + IR","paper":"/paper/improving-encoder-by-auxiliary-supervision","metrics":{"BLEU":"17.96"},"code_links":[{"title":"liang8qi/data2textwithauxiliarysupervision","url":"https://github.com/liang8qi/data2textwithauxiliarysupervision"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/data-to-text-generation-on-rotowire-relation","task":"Data-to-Text Generation","dataset_variant":"RotoWire (Relation Generation)","rows":6,"metrics":["Precision","count"],"first_row_in_archive_order":{"model":"SeqPlan","paper":"/paper/data-to-text-generation-with-variational","metrics":{"Precision":"97.6","count":"46.7"},"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"},{"leaderboard":"/sota/data-to-text-generation-on-rotowire-content","task":"Data-to-Text Generation","dataset_variant":"RotoWire (Content Ordering)","rows":5,"metrics":["DLD","BLEU"],"first_row_in_archive_order":{"model":"Hierarchical Transformer Encoder + conditional copy","paper":"/paper/a-hierarchical-model-for-data-to-text","metrics":{"BLEU":"17.50","DLD":"18.90%"},"code_links":[{"title":"KaijuML/data-to-text-hierarchical","url":"https://github.com/KaijuML/data-to-text-hierarchical"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/data-to-text-generation-on-rotowire-content-1","task":"Data-to-Text Generation","dataset_variant":"Rotowire (Content Selection)","rows":5,"metrics":["Precision","Recall"],"first_row_in_archive_order":{"model":"Hierarchical Transformer Encoder + conditional copy","paper":"/paper/a-hierarchical-model-for-data-to-text","metrics":{"Precision":"39.47%","Recall":"51.64%"},"code_links":[{"title":"KaijuML/data-to-text-hierarchical","url":"https://github.com/KaijuML/data-to-text-hierarchical"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/table-to-text-generation-on-rotowire","task":"Table-to-Text Generation","dataset_variant":"RotoWire","rows":1,"metrics":[" Content Ordering"," Content Selection (F1)","BLEU"],"first_row_in_archive_order":{"model":"HierarchicalEncoder + NR + IR","paper":"/paper/improving-encoder-by-auxiliary-supervision","metrics":{" Content Ordering":"25.30"," Content Selection (F1)":"55.88","BLEU":"17.96"},"code_links":[{"title":"liang8qi/data2textwithauxiliarysupervision","url":"https://github.com/liang8qi/data2textwithauxiliarysupervision"}]},"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":4,"code_links":0,"syntology":null},{"paper":"/paper/improving-encoder-by-auxiliary-supervision","title":"Improving Encoder by Auxiliary Supervision Tasks for Table-to-Text Generation","date":"2021-08-01","rows_on_this_dataset":2,"code_links":1,"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":4,"code_links":1,"syntology":null},{"paper":"/paper/a-hierarchical-model-for-data-to-text","title":"A Hierarchical Model for Data-to-Text Generation","date":"2019-12-20","rows_on_this_dataset":4,"code_links":1,"syntology":null},{"paper":"/paper/data-to-text-generation-with-content","title":"Data-to-Text Generation with Content Selection and Planning","date":"2018-09-03","rows_on_this_dataset":4,"code_links":2,"syntology":null},{"paper":"/paper/challenges-in-data-to-document-generation","title":"Challenges in Data-to-Document Generation","date":"2017-07-25","rows_on_this_dataset":4,"code_links":4,"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."}