{"url":"/dataset/genwiki","name":"GenWiki","full_name":null,"description_markdown":"GenWiki is a large-scale dataset for knowledge graph-to-text (G2T) and text-to-knowledge graph (T2G) conversion. It is introduced in the paper [\"GenWiki: A Dataset of 1.3 Million Content-Sharing Text and Graphs for Unsupervised Graph-to-Text Generation\"](https://www.aclweb.org/anthology/2020.coling-main.217.pdf) by Zhijing Jin, Qipeng Guo, Xipeng Qiu, and Zheng Zhang at COLING 2020.","description_withheld":null,"homepage":"https://github.com/zhijing-jin/genwiki","introduced_date":"2020-12-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/genwiki-a-dataset-of-1-3-million-content","title":"GenWiki: A Dataset of 1.3 Million Content-Sharing Text and Graphs for Unsupervised Graph-to-Text Generation","first_author":"Zhijing Jin","url":null},"license":{"name":"Unknown","url":null},"modalities":[{"name":"Graphs","url":"/datasets/modality/graphs"}],"tasks":[{"name":"Data-to-Text Generation","url":"/task/data-to-text-generation","datasets_with_task":"/datasets/task/data-to-text-generation"},{"name":"KG-to-Text Generation","url":"/task/kg-to-text","datasets_with_task":"/datasets/task/kg-to-text"},{"name":"Unsupervised KG-to-Text Generation","url":"/task/unsupervised-kg-to-text-generation","datasets_with_task":"/datasets/task/unsupervised-kg-to-text-generation"}],"languages":[],"variants":["GenWiki","GenWiki (Fine)","GenWiki (Full)"],"data_loaders":[{"repo":"https://github.com/zhijing-jin/genwiki","url":"https://github.com/zhijing-jin/genwiki","frameworks":[]}],"num_papers_in_archive":10,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/unsupervised-kg-to-text-generation-on-genwiki","task":"Unsupervised KG-to-Text Generation","dataset_variant":"GenWiki (Fine)","rows":5,"metrics":["BLEU","METEOR","ROUGE-L","CIDEr"],"first_row_in_archive_order":{"model":"CycleGT_Base","paper":"/paper/genwiki-a-dataset-of-1-3-million-content","metrics":{"BLEU":"41.59","CIDEr":"3.57","METEOR":"35.72","ROUGE-L":"63.31"},"code_links":[{"title":"zhijing-jin/genwiki","url":"https://github.com/zhijing-jin/genwiki"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/unsupervised-kg-to-text-generation-on-genwiki-1","task":"Unsupervised KG-to-Text Generation","dataset_variant":"GenWiki (Full)","rows":5,"metrics":["BLEU","METEOR","ROUGE-L","CIDEr"],"first_row_in_archive_order":{"model":"CycleGT_Base","paper":"/paper/genwiki-a-dataset-of-1-3-million-content","metrics":{"BLEU":"41.29","CIDEr":"3.53","METEOR":"35.39","ROUGE-L":"63.73"},"code_links":[{"title":"zhijing-jin/genwiki","url":"https://github.com/zhijing-jin/genwiki"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/data-to-text-generation-on-genwiki","task":"Data-to-Text Generation","dataset_variant":"GenWiki","rows":1,"metrics":["BLEU"],"first_row_in_archive_order":{"model":"T5-large","paper":"/paper/ontology-free-general-domain-knowledge-graph","metrics":{"BLEU":"45.85"},"code_links":[{"title":"daehuikim/WikiOFGraph","url":"https://github.com/daehuikim/WikiOFGraph"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/ontology-free-general-domain-knowledge-graph","title":"Ontology-Free General-Domain Knowledge Graph-to-Text Generation Dataset Synthesis using Large Language Model","date":"2024-09-11","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":7,"samples_ran":5,"samples_unverified":2,"pointer_only_for_licence":7,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/genwiki-a-dataset-of-1-3-million-content","title":"GenWiki: A Dataset of 1.3 Million Content-Sharing Text and Graphs for Unsupervised Graph-to-Text Generation","date":"2020-12-01","rows_on_this_dataset":10,"code_links":1,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":1,"samples_harvested":7,"samples_ran":5,"samples_unverified":2,"pointer_only_for_licence":7,"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."}