{"url":"/dataset/ccgbank","name":"CCGbank","full_name":null,"description_markdown":"**CCGbank** is a translation of the Penn Treebank into a corpus of Combinatory Categorial Grammar derivations. It pairs syntactic derivations with sets of word-word dependencies which approximate the underlying predicate-argument structure.\r\nThe dataset contains 99.44% of the sentences in the Penn Treebank, for which it corrects a number of inconsistencies and errors in the original annotation.\r\n\r\nSource: [CCGbank](https://catalog.ldc.upenn.edu/LDC2005T13)","description_withheld":null,"homepage":"https://catalog.ldc.upenn.edu/LDC2005T13","introduced_date":"2005-05-15","introduced_date_note":null,"introduced_by":null,"license":{"name":"Custom","url":"https://www.ldc.upenn.edu/language-resources/data/obtaining"},"modalities":[],"tasks":[{"name":"CCG Supertagging","url":"/task/ccg-supertagging","datasets_with_task":"/datasets/task/ccg-supertagging"}],"languages":[],"variants":[],"data_loaders":[{"repo":"https://github.com/allenai/allennlp-models","url":"https://docs.allennlp.org/models/main/models/tagging/dataset_readers/ccgbank/","frameworks":["pytorch"]}],"num_papers_in_archive":9,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/ccg-supertagging-on-ccgbank","task":"CCG Supertagging","dataset_variant":"CCGbank","rows":8,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Heterogeneous Dynamic Convolutions","paper":"/paper/geometry-aware-supertagging-with","metrics":{"Accuracy":"96.29"},"code_links":[{"title":"konstantinoskokos/spindle","url":"https://github.com/konstantinoskokos/spindle"},{"title":"konstantinoskokos/dynamic-graph-supertagging","url":"https://github.com/konstantinoskokos/dynamic-graph-supertagging"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/geometry-aware-supertagging-with","title":"Geometry-Aware Supertagging with Heterogeneous Dynamic Convolutions","date":"2022-03-23","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/supertagging-combinatory-categorial-grammar","title":"Supertagging Combinatory Categorial Grammar with Attentive Graph Convolutional Networks","date":"2020-10-13","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":2,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/hierarchically-refined-label-attention","title":"Hierarchically-Refined Label Attention Network for Sequence Labeling","date":"2019-08-23","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/semi-supervised-sequence-modeling-with-cross","title":"Semi-Supervised Sequence Modeling with Cross-View Training","date":"2018-09-22","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/deep-multi-task-learning-with-low-level-tasks","title":"Deep multi-task learning with low level tasks supervised at lower layers","date":"2016-08-01","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/supertagging-with-lstms","title":"Supertagging With LSTMs","date":"2016-06-01","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/lstm-ccg-parsing","title":"LSTM CCG Parsing","date":"2016-06-01","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/ccg-supertagging-with-a-recurrent-neural","title":"CCG Supertagging with a Recurrent Neural Network","date":"2015-07-01","rows_on_this_dataset":1,"code_links":0,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":1,"samples_harvested":2,"samples_ran":2,"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."}