{"url":"/task/kg-to-text","name":"KG-to-Text Generation","slug":"kg-to-text","description_markdown":"Knowledge-graph-to-text (KG-to-text) generation aims to generate high-quality texts which are consistent with input graphs.\r\n\r\nDescription from: [JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge Graphs](https://arxiv.org/pdf/2106.10502v1.pdf)","categories":[{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":22,"papers_with_code":18,"benchmarks":11,"benchmark_tables_in_archive":11,"benchmark_tables_shown":11,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":9,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/kg-to-text-generation-on-webnlg-2-0","slug":"kg-to-text-generation-on-webnlg-2-0","dataset":"WebNLG 2.0 (Unconstrained)","dataset_url":"/dataset/webnlg","rows_in_archive":13,"metrics":["BLEU","METEOR","ROUGE"],"first_row_in_archive_order":{"model":"GAP - Me,r+γ","paper_title":"GAP: A Graph-aware Language Model Framework for Knowledge Graph-to-Text Generation","paper_url":"/paper/gap-a-graph-aware-language-model-framework","paper_date":"2022-04-13","arxiv_id":"2204.06674","code_links":[{"title":"acolas1/GAP_COLING2022","url":"https://github.com/acolas1/GAP_COLING2022"}],"syntology":null}},{"leaderboard":"/sota/kg-to-text-generation-on-webnlg-2-0-1","slug":"kg-to-text-generation-on-webnlg-2-0-1","dataset":"WebNLG 2.0 (Constrained)","dataset_url":"/dataset/webnlg","rows_in_archive":9,"metrics":["BLEU","METEOR","ROUGE","FactSpotter"],"first_row_in_archive_order":{"model":"FactT5B","paper_title":"FactSpotter: Evaluating the Factual Faithfulness of Graph-to-Text Generation","paper_url":"/paper/factspotter-evaluating-the-factual","paper_date":"2023-10-25","arxiv_id":null,"code_links":[{"title":"guihuzhang/FactSpotter","url":"https://github.com/guihuzhang/FactSpotter"}],"syntology":null}},{"leaderboard":"/sota/kg-to-text-generation-on-eventnarrative","slug":"kg-to-text-generation-on-eventnarrative","dataset":"EventNarrative","dataset_url":"/dataset/eventnarrative","rows_in_archive":8,"metrics":["BLEU","METEOR","ROUGE","BertScore","CIDEr","ChrF++"],"first_row_in_archive_order":{"model":"GAP - Me,r+γ","paper_title":"GAP: A Graph-aware Language Model Framework for Knowledge Graph-to-Text Generation","paper_url":"/paper/gap-a-graph-aware-language-model-framework","paper_date":"2022-04-13","arxiv_id":"2204.06674","code_links":[{"title":"acolas1/GAP_COLING2022","url":"https://github.com/acolas1/GAP_COLING2022"}],"syntology":null}},{"leaderboard":"/sota/kg-to-text-generation-on-agenda","slug":"kg-to-text-generation-on-agenda","dataset":"AGENDA","dataset_url":"/dataset/agenda","rows_in_archive":6,"metrics":["BLEU"],"first_row_in_archive_order":{"model":"BART-large+ STA","paper_title":"Investigating Pretrained Language Models for Graph-to-Text Generation","paper_url":"/paper/investigating-pretrained-language-models-for","paper_date":"2020-07-16","arxiv_id":"2007.08426","code_links":[{"title":"bjascob/amrlib","url":"https://github.com/bjascob/amrlib"},{"title":"UKPLab/plms-graph2text","url":"https://github.com/UKPLab/plms-graph2text"},{"title":"ukplab/m-amr2text","url":"https://github.com/ukplab/m-amr2text"}],"syntology":{"n":12,"n_ran":2,"n_unverified":10,"n_pointer_only":0}}},{"leaderboard":"/sota/kg-to-text-generation-on-pathquestion","slug":"kg-to-text-generation-on-pathquestion","dataset":"PathQuestion","dataset_url":"/dataset/pathquestion","rows_in_archive":5,"metrics":["BLEU","METEOR","ROUGE"],"first_row_in_archive_order":{"model":"JointGT (BART)","paper_title":"JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge Graphs","paper_url":"/paper/jointgt-graph-text-joint-representation","paper_date":"2021-06-19","arxiv_id":"2106.10502","code_links":[{"title":"thu-coai/JointGT","url":"https://github.com/thu-coai/JointGT"}],"syntology":null}},{"leaderboard":"/sota/kg-to-text-generation-on-webquestions","slug":"kg-to-text-generation-on-webquestions","dataset":"WebQuestions","dataset_url":"/dataset/webquestions","rows_in_archive":5,"metrics":["BLEU","METEOR","ROUGE"],"first_row_in_archive_order":{"model":"JointGT (BART)","paper_title":"JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge Graphs","paper_url":"/paper/jointgt-graph-text-joint-representation","paper_date":"2021-06-19","arxiv_id":"2106.10502","code_links":[{"title":"thu-coai/JointGT","url":"https://github.com/thu-coai/JointGT"}],"syntology":null}},{"leaderboard":"/sota/kg-to-text-generation-on-wikigraphs","slug":"kg-to-text-generation-on-wikigraphs","dataset":"WikiGraphs","dataset_url":"/dataset/wikigraphs","rows_in_archive":4,"metrics":["Test perplexity","rBLEU (Test)","rBLEU (Valid)","rBLEU(w/title)(Test)","rBLEU(w/title)(Valid)"],"first_row_in_archive_order":{"model":"Unconditional","paper_title":"WikiGraphs: A Wikipedia Text - Knowledge Graph Paired Dataset","paper_url":"/paper/wikigraphs-a-wikipedia-text-knowledge-graph","paper_date":"2021-07-20","arxiv_id":"2107.09556","code_links":[{"title":"deepmind/deepmind-research","url":"https://github.com/deepmind/deepmind-research/tree/master/wikigraphs"}],"syntology":null}},{"leaderboard":"/sota/kg-to-text-generation-on-webnlg-all","slug":"kg-to-text-generation-on-webnlg-all","dataset":"WebNLG (All)","dataset_url":"/dataset/webnlg","rows_in_archive":2,"metrics":["BLEU","METEOR","chrF++"],"first_row_in_archive_order":{"model":"T5_large","paper_title":"Investigating Pretrained Language Models for Graph-to-Text Generation","paper_url":"/paper/investigating-pretrained-language-models-for","paper_date":"2020-07-16","arxiv_id":"2007.08426","code_links":[{"title":"bjascob/amrlib","url":"https://github.com/bjascob/amrlib"},{"title":"UKPLab/plms-graph2text","url":"https://github.com/UKPLab/plms-graph2text"},{"title":"ukplab/m-amr2text","url":"https://github.com/ukplab/m-amr2text"}],"syntology":{"n":12,"n_ran":2,"n_unverified":10,"n_pointer_only":0}}},{"leaderboard":"/sota/kg-to-text-generation-on-webnlg-seen","slug":"kg-to-text-generation-on-webnlg-seen","dataset":"WebNLG (Seen)","dataset_url":"/dataset/webnlg","rows_in_archive":2,"metrics":["BLEU","METEOR","chrF++"],"first_row_in_archive_order":{"model":"T5_large","paper_title":"Investigating Pretrained Language Models for Graph-to-Text Generation","paper_url":"/paper/investigating-pretrained-language-models-for","paper_date":"2020-07-16","arxiv_id":"2007.08426","code_links":[{"title":"bjascob/amrlib","url":"https://github.com/bjascob/amrlib"},{"title":"UKPLab/plms-graph2text","url":"https://github.com/UKPLab/plms-graph2text"},{"title":"ukplab/m-amr2text","url":"https://github.com/ukplab/m-amr2text"}],"syntology":{"n":12,"n_ran":2,"n_unverified":10,"n_pointer_only":0}}},{"leaderboard":"/sota/kg-to-text-generation-on-webnlg-unseen","slug":"kg-to-text-generation-on-webnlg-unseen","dataset":"WebNLG (Unseen)","dataset_url":"/dataset/webnlg","rows_in_archive":2,"metrics":["BLEU","METEOR","chrF++"],"first_row_in_archive_order":{"model":"T5_large","paper_title":"Investigating Pretrained Language Models for Graph-to-Text Generation","paper_url":"/paper/investigating-pretrained-language-models-for","paper_date":"2020-07-16","arxiv_id":"2007.08426","code_links":[{"title":"bjascob/amrlib","url":"https://github.com/bjascob/amrlib"},{"title":"UKPLab/plms-graph2text","url":"https://github.com/UKPLab/plms-graph2text"},{"title":"ukplab/m-amr2text","url":"https://github.com/ukplab/m-amr2text"}],"syntology":{"n":12,"n_ran":2,"n_unverified":10,"n_pointer_only":0}}},{"leaderboard":"/sota/kg-to-text-generation-on-ent-desc","slug":"kg-to-text-generation-on-ent-desc","dataset":"ENT-DESC","dataset_url":"/dataset/ent-desc","rows_in_archive":1,"metrics":["BLEU"],"first_row_in_archive_order":{"model":"MGCN+sum","paper_title":"ENT-DESC: Entity Description Generation by Exploring Knowledge Graph","paper_url":"/paper/knowledge-graph-empowered-entity-description","paper_date":"2020-04-30","arxiv_id":"2004.14813","code_links":[{"title":"LiyingCheng95/EntityDescriptionGeneration","url":"https://github.com/LiyingCheng95/EntityDescriptionGeneration"}],"syntology":null}}],"datasets":[{"url":"/dataset/webquestions","name":"WebQuestions","full_name":"","num_papers_in_archive":241},{"url":"/dataset/webnlg","name":"WebNLG","full_name":"","num_papers_in_archive":149},{"url":"/dataset/agenda","name":"AGENDA","full_name":"Abstract GENeration DAtaset","num_papers_in_archive":19},{"url":"/dataset/genwiki","name":"GenWiki","full_name":"","num_papers_in_archive":10},{"url":"/dataset/pathquestion","name":"PathQuestion","full_name":"","num_papers_in_archive":7},{"url":"/dataset/wikigraphs","name":"WikiGraphs","full_name":"","num_papers_in_archive":4},{"url":"/dataset/eventnarrative","name":"EventNarrative","full_name":"","num_papers_in_archive":3},{"url":"/dataset/xalign","name":"XAlign","full_name":"","num_papers_in_archive":2},{"url":"/dataset/ent-desc","name":"ENT-DESC","full_name":"","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[{"url":"/task/data-to-text-generation","name":"Data-to-Text Generation"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":18,"of":18,"tagged_in_all":22,"items":[{"url":"/paper/investigating-pretrained-language-models-for","title":"Investigating Pretrained Language Models for Graph-to-Text Generation","date":"2020-07-16","arxiv_id":"2007.08426","repositories_listed":3,"syntology":{"n":12,"n_ran":2,"n_unverified":10,"n_pointer_only":0}},{"url":"/paper/text-generation-from-knowledge-graphs-with","title":"Text Generation from Knowledge Graphs with Graph Transformers","date":"2019-04-04","arxiv_id":"1904.02342","repositories_listed":3,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/handling-rare-items-in-data-to-text","title":"Handling Rare Items in Data-to-Text Generation","date":"2018-11-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/deep-graph-convolutional-encoders-for","title":"Deep Graph Convolutional Encoders for Structured Data to Text Generation","date":"2018-10-23","arxiv_id":"1810.09995","repositories_listed":2,"syntology":{"n":3,"n_ran":1,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/factspotter-evaluating-the-factual","title":"FactSpotter: Evaluating the Factual Faithfulness of Graph-to-Text Generation","date":"2023-10-25","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/can-knowledge-graphs-simplify-text","title":"Can Knowledge Graphs Simplify Text?","date":"2023-08-14","arxiv_id":"2308.06975","repositories_listed":1,"syntology":null},{"url":"/paper/using-large-language-models-for-zero-shot","title":"Using Large Language Models for Zero-Shot Natural Language Generation from Knowledge Graphs","date":"2023-07-14","arxiv_id":"2307.07312","repositories_listed":1,"syntology":null},{"url":"/paper/syntax-controlled-knowledge-graph-to-text","title":"Syntax Controlled Knowledge Graph-to-Text Generation with Order and Semantic Consistency","date":"2022-07-02","arxiv_id":"2207.00719","repositories_listed":1,"syntology":null},{"url":"/paper/gap-a-graph-aware-language-model-framework","title":"GAP: A Graph-aware Language Model Framework for Knowledge Graph-to-Text Generation","date":"2022-04-13","arxiv_id":"2204.06674","repositories_listed":1,"syntology":null},{"url":"/paper/eventnarrative-a-large-scale-event-centric","title":"EventNarrative: A large-scale Event-centric Dataset for Knowledge Graph-to-Text Generation","date":"2021-10-30","arxiv_id":"2111.00276","repositories_listed":1,"syntology":null},{"url":"/paper/wikigraphs-a-wikipedia-text-knowledge-graph","title":"WikiGraphs: A Wikipedia Text - Knowledge Graph Paired Dataset","date":"2021-07-20","arxiv_id":"2107.09556","repositories_listed":1,"syntology":null},{"url":"/paper/jointgt-graph-text-joint-representation","title":"JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge Graphs","date":"2021-06-19","arxiv_id":"2106.10502","repositories_listed":1,"syntology":null},{"url":"/paper/few-shot-knowledge-graph-to-text-generation","title":"Few-shot Knowledge Graph-to-Text Generation with Pretrained Language Models","date":"2021-06-03","arxiv_id":"2106.01623","repositories_listed":1,"syntology":null},{"url":"/paper/how-to-train-your-agent-to-read-and-write","title":"How to Train Your Agent to Read and Write","date":"2021-01-04","arxiv_id":"2101.00916","repositories_listed":1,"syntology":null},{"url":"/paper/kgpt-knowledge-grounded-pre-training-for-data","title":"KGPT: Knowledge-Grounded Pre-Training for Data-to-Text Generation","date":"2020-10-05","arxiv_id":"2010.02307","repositories_listed":1,"syntology":null},{"url":"/paper/knowledge-graph-empowered-entity-description","title":"ENT-DESC: Entity Description Generation by Exploring Knowledge Graph","date":"2020-04-30","arxiv_id":"2004.14813","repositories_listed":1,"syntology":null},{"url":"/paper/toward-subgraph-guided-knowledge-graph","title":"Toward Subgraph-Guided Knowledge Graph Question Generation with Graph Neural Networks","date":"2020-04-13","arxiv_id":"2004.06015","repositories_listed":1,"syntology":{"n":5,"n_ran":0,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/modeling-global-and-local-node-contexts-for","title":"Modeling Global and Local Node Contexts for Text Generation from Knowledge Graphs","date":"2020-01-29","arxiv_id":"2001.11003","repositories_listed":1,"syntology":null}],"syntology_records":4,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}