{"url":"/dataset/conll-2009","name":"CoNLL-2009","full_name":"CoNLL-2009","description_markdown":"The task builds on the CoNLL-2008 task and extends it to multiple languages. The core of the task is to predict syntactic and semantic dependencies and their labeling. Data is provided for both statistical training and evaluation, which extract these labeled dependencies from manually annotated treebanks such as the Penn Treebank for English, the Prague Dependency Treebank for Czech and similar treebanks for Catalan, Chinese, German, Japanese and Spanish languages, enriched with semantic relations (such as those captured in the Prop/Nombank and similar resources). Great effort has been devoted to provide the participants with a common and relatively simple data representation for all the languages, similar to the last year's English data.","description_withheld":null,"homepage":"https://catalog.ldc.upenn.edu/LDC2012T04","introduced_date":"2012-04-20","introduced_date_note":null,"introduced_by":null,"license":null,"modalities":[],"tasks":[{"name":"Dependency Parsing","url":"/task/dependency-parsing","datasets_with_task":"/datasets/task/dependency-parsing"},{"name":"Semantic Role Labeling","url":"/task/semantic-role-labeling","datasets_with_task":"/datasets/task/semantic-role-labeling"},{"name":"Chinese Semantic Role Labeling","url":"/task/chinese-semantic-role-labeling","datasets_with_task":"/datasets/task/chinese-semantic-role-labeling"}],"languages":[],"variants":["CoNLL-2009"],"data_loaders":[],"num_papers_in_archive":8,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/dependency-parsing-on-conll-2009","task":"Dependency Parsing","dataset_variant":"CoNLL-2009","rows":2,"metrics":["LAS","UAS"],"first_row_in_archive_order":{"model":"CRFPar","paper":"/paper/efficient-second-order-treecrf-for-neural","metrics":{"LAS":"86.52","UAS":"89.63"},"code_links":[{"title":"yzhangcs/parser","url":"https://github.com/yzhangcs/parser"},{"title":"yzhangcs/crfpar","url":"https://github.com/yzhangcs/crfpar"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/semantic-role-labeling-on-conll-2009","task":"Semantic Role Labeling","dataset_variant":"CoNLL-2009","rows":1,"metrics":["F1 (Arg.)","F1 (Prd.)"],"first_row_in_archive_order":{"model":"Ours (High-Order model)","paper":"/paper/end-to-end-semantic-role-labeling-with-neural","metrics":{"F1 (Arg.)":"90.2","F1 (Prd.)":"95.5"},"code_links":[{"title":"scofield7419/TransitionSRL","url":"https://github.com/scofield7419/TransitionSRL"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/end-to-end-semantic-role-labeling-with-neural","title":"End-to-end Semantic Role Labeling with Neural Transition-based Model","date":"2021-01-02","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/efficient-second-order-treecrf-for-neural","title":"Efficient Second-Order TreeCRF for Neural Dependency Parsing","date":"2020-05-03","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":2,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/deep-biaffine-attention-for-neural-dependency","title":"Deep Biaffine Attention for Neural Dependency Parsing","date":"2016-11-06","rows_on_this_dataset":1,"code_links":26,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":19,"samples_ran":3,"samples_unverified":16,"pointer_only_for_licence":2,"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":2,"samples_harvested":22,"samples_ran":5,"samples_unverified":17,"pointer_only_for_licence":2,"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."}