{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/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","arxiv_id":null,"date":"2020-12-01","proceeding":"COLING 2020 8","authors":["Zhijing Jin","Qipeng Guo","Xipeng Qiu","Zheng Zhang"],"abstract":"Data collection for the knowledge graph-to-text generation is expensive. As a result, research on unsupervised models has emerged as an active field recently. However, most unsupervised models have to use non-parallel versions of existing small supervised datasets, which largely constrain their potential. In this paper, we propose a large-scale, general-domain dataset, GenWiki. Our unsupervised dataset has 1.3M text and graph examples, respectively. With a human-annotated test set, we provide this new benchmark dataset for future research on unsupervised text generation from knowledge graphs.","url_abs":"https://aclanthology.org/2020.coling-main.217/","url_pdf":"https://aclanthology.org/2020.coling-main.217.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"genwiki-a-dataset-of-1-3-million-content","repo_url":"https://github.com/zhijing-jin/genwiki","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"knowledge-graphs","task_name":"Knowledge Graphs"},{"task_slug":"text-generation","task_name":"Text Generation"},{"task_slug":"unsupervised-kg-to-text-generation","task_name":"Unsupervised KG-to-Text Generation"}],"methods":[],"datasets_introduced":[{"slug":"genwiki","name":"GenWiki","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/unsupervised-kg-to-text-generation-on-genwiki","task":"Unsupervised KG-to-Text Generation","dataset":"GenWiki (Fine)","model":"CycleGT_Base","rank_in_archive_order":1,"of":5,"metrics":{"BLEU":"41.59","CIDEr":"3.57","METEOR":"35.72","ROUGE-L":"63.31"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-kg-to-text-generation-on-genwiki","task":"Unsupervised KG-to-Text Generation","dataset":"GenWiki (Fine)","model":"CycleGT_Warm","rank_in_archive_order":2,"of":5,"metrics":{"BLEU":"41.35","CIDEr":"3.45","METEOR":"35.20","ROUGE-L":"63.01"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-kg-to-text-generation-on-genwiki","task":"Unsupervised KG-to-Text Generation","dataset":"GenWiki (Fine)","model":"NoisySupervised","rank_in_archive_order":3,"of":5,"metrics":{"BLEU":"30.12","CIDEr":"2.52","METEOR":"28.12","ROUGE-L":"56.96"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-kg-to-text-generation-on-genwiki","task":"Unsupervised KG-to-Text Generation","dataset":"GenWiki (Fine)","model":"DirectTransfer","rank_in_archive_order":4,"of":5,"metrics":{"BLEU":"13.89","CIDEr":"1.26","METEOR":"25.76","ROUGE-L":"39.75"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-kg-to-text-generation-on-genwiki","task":"Unsupervised KG-to-Text Generation","dataset":"GenWiki (Fine)","model":"Rule-Based","rank_in_archive_order":5,"of":5,"metrics":{"BLEU":"13.45","CIDEr":"1.26","METEOR":"30.72","ROUGE-L":"40.93"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-kg-to-text-generation-on-genwiki-1","task":"Unsupervised KG-to-Text Generation","dataset":"GenWiki (Full)","model":"CycleGT_Base","rank_in_archive_order":1,"of":5,"metrics":{"BLEU":"41.29","CIDEr":"3.53","METEOR":"35.39","ROUGE-L":"63.73"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-kg-to-text-generation-on-genwiki-1","task":"Unsupervised KG-to-Text Generation","dataset":"GenWiki (Full)","model":"CycleGT_Warm","rank_in_archive_order":2,"of":5,"metrics":{"BLEU":"40.47","CIDEr":"3.48","METEOR":"34.84","ROUGE-L":"63.40"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-kg-to-text-generation-on-genwiki-1","task":"Unsupervised KG-to-Text Generation","dataset":"GenWiki (Full)","model":"NoisySupervised","rank_in_archive_order":3,"of":5,"metrics":{"BLEU":"35.03","CIDEr":"2.63","METEOR":"33.45","ROUGE-L":"58.14"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-kg-to-text-generation-on-genwiki-1","task":"Unsupervised KG-to-Text Generation","dataset":"GenWiki (Full)","model":"DirectTransfer","rank_in_archive_order":4,"of":5,"metrics":{"BLEU":"13.89","CIDEr":"1.26","METEOR":"25.76","ROUGE-L":"39.75"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-kg-to-text-generation-on-genwiki-1","task":"Unsupervised KG-to-Text Generation","dataset":"GenWiki (Full)","model":"Rule-Based","rank_in_archive_order":5,"of":5,"metrics":{"BLEU":"13.45","CIDEr":"1.26","METEOR":"30.72","ROUGE-L":"40.93"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}