{"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/ontology-free-general-domain-knowledge-graph","title":"Ontology-Free General-Domain Knowledge Graph-to-Text Generation Dataset Synthesis using Large Language Model","arxiv_id":"2409.07088","date":"2024-09-11","proceeding":null,"authors":["Daehee Kim","Deokhyung Kang","Sangwon Ryu","Gary Geunbae Lee"],"abstract":"Knowledge Graph-to-Text (G2T) generation involves verbalizing structured knowledge graphs into natural language text. Recent advancements in Pretrained Language Models (PLMs) have improved G2T performance, but their effectiveness depends on datasets with precise graph-text alignment. However, the scarcity of high-quality, general-domain G2T generation datasets restricts progress in the general-domain G2T generation research. To address this issue, we introduce Wikipedia Ontology-Free Graph-text dataset (WikiOFGraph), a new large-scale G2T dataset generated using a novel method that leverages Large Language Model (LLM) and Data-QuestEval. Our new dataset, which contains 5.85M general-domain graph-text pairs, offers high graph-text consistency without relying on external ontologies. Experimental results demonstrate that PLM fine-tuned on WikiOFGraph outperforms those trained on other datasets across various evaluation metrics. Our method proves to be a scalable and effective solution for generating high-quality G2T data, significantly advancing the field of G2T generation.","url_abs":"https://arxiv.org/abs/2409.07088v1","url_pdf":"https://arxiv.org/pdf/2409.07088v1.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":"ontology-free-general-domain-knowledge-graph","repo_url":"https://github.com/daehuikim/WikiOFGraph","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"data-to-text-generation","task_name":"Data-to-Text Generation"},{"task_slug":"graph-to-sequence","task_name":"Graph-to-Sequence"},{"task_slug":"knowledge-graphs","task_name":"Knowledge Graphs"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"large-language-model","task_name":"Large Language Model"},{"task_slug":"text-generation","task_name":"Text Generation"}],"methods":[],"datasets_introduced":[{"slug":"wikiofgraph","name":"WikiOFGraph","full_name":"Wikipedia Ontology-Free Graph-Text"}],"methods_introduced":[],"results":[{"leaderboard":"/sota/data-to-text-generation-on-genwiki","task":"Data-to-Text Generation","dataset":"GenWiki","model":"T5-large","rank_in_archive_order":1,"of":1,"metrics":{"BLEU":"45.85"},"uses_additional_data":false},{"leaderboard":"/sota/data-to-text-generation-on-wikiofgraph","task":"Data-to-Text Generation","dataset":"WikiOFGraph","model":"T5-large","rank_in_archive_order":1,"of":1,"metrics":{"BLEU":"69.27"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2409.07088","atlas_url":"https://app.syntology.ai/?focus=2409.07088","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.07088"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/daehuikim/WikiOFGraph","reach":{"status":"ok"}}],"summary":{"ran":4,"ran_honours":1,"unverified":2},"by_repo_kind":{"official":{"samples":7,"ran":5,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":7,"samples":[{"code_sha256_prefix":"93591c49a35428cc","entry":"calculate_f1_squad","repo":"daehuikim/WikiOFGraph","repo_kind":"official","path":"qeval/questeval/utils.py","file_url":"https://github.com/daehuikim/WikiOFGraph/blob/HEAD/qeval/questeval/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"93591c49a35428cc"}},{"code_sha256_prefix":"d2895bdf14e8f94f","entry":"preprocess_logits_for_metrics","repo":"daehuikim/WikiOFGraph","repo_kind":"official","path":"experiments/t5_trainer.py","file_url":"https://github.com/daehuikim/WikiOFGraph/blob/HEAD/experiments/t5_trainer.py","link_basis":"plan_row","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d2895bdf14e8f94f"}},{"code_sha256_prefix":"1e042a49b658598e","entry":"split_tokens","repo":"daehuikim/WikiOFGraph","repo_kind":"official","path":"experiments/t5_trainer.py","file_url":"https://github.com/daehuikim/WikiOFGraph/blob/HEAD/experiments/t5_trainer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1e042a49b658598e"}},{"code_sha256_prefix":"f1f5b3d2bb080fa6","entry":"text2hash","repo":"daehuikim/WikiOFGraph","repo_kind":"official","path":"qeval/questeval/utils.py","file_url":"https://github.com/daehuikim/WikiOFGraph/blob/HEAD/qeval/questeval/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f1f5b3d2bb080fa6"}},{"code_sha256_prefix":"95f427aa3b9319b2","entry":"transfer_style","repo":"daehuikim/WikiOFGraph","repo_kind":"official","path":"qualitativeAnalysis/gpteval.py","file_url":"https://github.com/daehuikim/WikiOFGraph/blob/HEAD/qualitativeAnalysis/gpteval.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"95f427aa3b9319b2"}},{"code_sha256_prefix":"99471b0d5cf353cb","entry":"compute_metrics_bleu","repo":"daehuikim/WikiOFGraph","repo_kind":"official","path":"experiments/t5_trainer.py","file_url":"https://github.com/daehuikim/WikiOFGraph/blob/HEAD/experiments/t5_trainer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"99471b0d5cf353cb"}},{"code_sha256_prefix":"da019af8c804ce0a","entry":"sentencize","repo":"daehuikim/WikiOFGraph","repo_kind":"official","path":"qeval/questeval/utils.py","file_url":"https://github.com/daehuikim/WikiOFGraph/blob/HEAD/qeval/questeval/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"da019af8c804ce0a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}