{"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/investigating-pretrained-language-models-for","title":"Investigating Pretrained Language Models for Graph-to-Text Generation","arxiv_id":"2007.08426","date":"2020-07-16","proceeding":"EMNLP (NLP4ConvAI) 2021 11","authors":["Leonardo F. R. Ribeiro","Martin Schmitt","Hinrich Schütze","Iryna Gurevych"],"abstract":"Graph-to-text generation aims to generate fluent texts from graph-based data. In this paper, we investigate two recently proposed pretrained language models (PLMs) and analyze the impact of different task-adaptive pretraining strategies for PLMs in graph-to-text generation. We present a study across three graph domains: meaning representations, Wikipedia knowledge graphs (KGs) and scientific KGs. We show that the PLMs BART and T5 achieve new state-of-the-art results and that task-adaptive pretraining strategies improve their performance even further. In particular, we report new state-of-the-art BLEU scores of 49.72 on LDC2017T10, 59.70 on WebNLG, and 25.66 on AGENDA datasets - a relative improvement of 31.8%, 4.5%, and 42.4%, respectively. In an extensive analysis, we identify possible reasons for the PLMs' success on graph-to-text tasks. We find evidence that their knowledge about true facts helps them perform well even when the input graph representation is reduced to a simple bag of node and edge labels.","url_abs":"https://arxiv.org/abs/2007.08426v3","url_pdf":"https://arxiv.org/pdf/2007.08426v3.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":"investigating-pretrained-language-models-for","repo_url":"https://github.com/UKPLab/plms-graph2text","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"investigating-pretrained-language-models-for","repo_url":"https://github.com/bjascob/amrlib","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"investigating-pretrained-language-models-for","repo_url":"https://github.com/ukplab/m-amr2text","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"amr-to-text-generation","task_name":"AMR-to-Text Generation"},{"task_slug":"data-to-text-generation","task_name":"Data-to-Text Generation"},{"task_slug":"kb-to-language-generation","task_name":"KB-to-Language Generation"},{"task_slug":"kg-to-text","task_name":"KG-to-Text Generation"},{"task_slug":"knowledge-graphs","task_name":"Knowledge Graphs"},{"task_slug":"question-generation","task_name":"Question Generation"},{"task_slug":"text-generation","task_name":"Text Generation"}],"methods":[{"method_slug":"adafactor","method_name":"Adafactor"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bart","method_name":"BART"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"glu","method_name":"Gated Linear Unit"},{"method_slug":"inverse-square-root-schedule","method_name":"Inverse Square Root Schedule"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"sentencepiece","method_name":"SentencePiece"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"t5","method_name":"T5"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/data-to-text-generation-on-webnlg","task":"Data-to-Text Generation","dataset":"WebNLG","model":"T5-small","rank_in_archive_order":9,"of":20,"metrics":{"BLEU":"65.05"},"uses_additional_data":false},{"leaderboard":"/sota/data-to-text-generation-on-webnlg-full-1","task":"Data-to-Text Generation","dataset":"WebNLG Full","model":"T5-large","rank_in_archive_order":4,"of":8,"metrics":{"BLEU":"59.70"},"uses_additional_data":false},{"leaderboard":"/sota/kg-to-text-generation-on-agenda","task":"KG-to-Text Generation","dataset":"AGENDA","model":"BART-large+ STA","rank_in_archive_order":1,"of":6,"metrics":{"BLEU":"25.66"},"uses_additional_data":true},{"leaderboard":"/sota/kg-to-text-generation-on-agenda","task":"KG-to-Text Generation","dataset":"AGENDA","model":"BART-large","rank_in_archive_order":2,"of":6,"metrics":{"BLEU":"23.65"},"uses_additional_data":false},{"leaderboard":"/sota/kg-to-text-generation-on-webnlg-all","task":"KG-to-Text Generation","dataset":"WebNLG (All)","model":"T5_large","rank_in_archive_order":1,"of":2,"metrics":{"BLEU":"59.70","METEOR":"44.18","chrF++":"75.40"},"uses_additional_data":false},{"leaderboard":"/sota/kg-to-text-generation-on-webnlg-all","task":"KG-to-Text Generation","dataset":"WebNLG (All)","model":"BART_large","rank_in_archive_order":2,"of":2,"metrics":{"BLEU":"54.72","METEOR":"42.23","chrF++":"72.29"},"uses_additional_data":false},{"leaderboard":"/sota/kg-to-text-generation-on-webnlg-seen","task":"KG-to-Text Generation","dataset":"WebNLG (Seen)","model":"T5_large","rank_in_archive_order":1,"of":2,"metrics":{"BLEU":"64.71","METEOR":"45.85","chrF++":"78.29"},"uses_additional_data":false},{"leaderboard":"/sota/kg-to-text-generation-on-webnlg-seen","task":"KG-to-Text Generation","dataset":"WebNLG (Seen)","model":"BART_large","rank_in_archive_order":2,"of":2,"metrics":{"BLEU":"63.45","METEOR":"45.49","chrF++":"77.57"},"uses_additional_data":false},{"leaderboard":"/sota/kg-to-text-generation-on-webnlg-unseen","task":"KG-to-Text Generation","dataset":"WebNLG (Unseen)","model":"T5_large","rank_in_archive_order":1,"of":2,"metrics":{"BLEU":"53.67","METEOR":"42.26","chrF++":"72.25"},"uses_additional_data":false},{"leaderboard":"/sota/kg-to-text-generation-on-webnlg-unseen","task":"KG-to-Text Generation","dataset":"WebNLG (Unseen)","model":"BART_large","rank_in_archive_order":2,"of":2,"metrics":{"BLEU":"43.97","METEOR":"38.61","chrF++":"66.53"},"uses_additional_data":false},{"leaderboard":"/sota/question-generation-on-grailqa-compositional","task":"Question Generation","dataset":"GrailQA-Compositional","model":"T5B","rank_in_archive_order":4,"of":4,"metrics":{"BLEU":"31.75","FactSpotter":"94.84","METEOR":"35.64"},"uses_additional_data":false},{"leaderboard":"/sota/question-generation-on-grailqa-iid","task":"Question Generation","dataset":"GrailQA-IID","model":"T5B","rank_in_archive_order":3,"of":4,"metrics":{"BLEU":"44.51","FactSpotter":"99.43","METEOR":"42.71"},"uses_additional_data":false},{"leaderboard":"/sota/question-generation-on-grailqa-zero-shot","task":"Question Generation","dataset":"GrailQA-Zero-Shot","model":"T5B","rank_in_archive_order":4,"of":4,"metrics":{"FactSpotter":"94.77","METEOR":"37.35","bleu":"32.20"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2007.08426","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.08426"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/UKPLab/plms-graph2text","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ukplab/m-amr2text","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/bjascob/amrlib","reach":null}],"summary":{"ran":2,"unverified":10},"by_repo_kind":{"official":{"samples":12,"ran":2,"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":0,"samples":[{"code_sha256_prefix":"a3826392847cbef3","entry":"count_trainable_parameters","repo":"UKPLab/plms-graph2text","repo_kind":"official","path":"agenda/callbacks.py","file_url":"https://github.com/UKPLab/plms-graph2text/blob/HEAD/agenda/callbacks.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a3826392847cbef3"}},{"code_sha256_prefix":"295d9fdc5ce0b054","entry":"get_early_stopping_callback","repo":"UKPLab/plms-graph2text","repo_kind":"official","path":"agenda/callbacks.py","file_url":"https://github.com/UKPLab/plms-graph2text/blob/HEAD/agenda/callbacks.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"295d9fdc5ce0b054"}},{"code_sha256_prefix":"9490bc2c5dd83c43","entry":"convert_text","repo":"UKPLab/plms-graph2text","repo_kind":"official","path":"agenda/utils_graph2text.py","file_url":"https://github.com/UKPLab/plms-graph2text/blob/HEAD/agenda/utils_graph2text.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9490bc2c5dd83c43"}},{"code_sha256_prefix":"3ea4bb27e2072f0b","entry":"convert_text","repo":"UKPLab/plms-graph2text","repo_kind":"official","path":"amr/utils_graph2text.py","file_url":"https://github.com/UKPLab/plms-graph2text/blob/HEAD/amr/utils_graph2text.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3ea4bb27e2072f0b"}},{"code_sha256_prefix":"99630a47929b50fd","entry":"eval_bleu_sents","repo":"UKPLab/plms-graph2text","repo_kind":"official","path":"amr/utils_graph2text.py","file_url":"https://github.com/UKPLab/plms-graph2text/blob/HEAD/amr/utils_graph2text.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"99630a47929b50fd"}},{"code_sha256_prefix":"bd41c2ca209d74c8","entry":"eval_bleu_sents_tok","repo":"UKPLab/plms-graph2text","repo_kind":"official","path":"amr/utils_graph2text.py","file_url":"https://github.com/UKPLab/plms-graph2text/blob/HEAD/amr/utils_graph2text.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"bd41c2ca209d74c8"}},{"code_sha256_prefix":"16c9346aec54122b","entry":"eval_chrf_test_webnlg","repo":"UKPLab/plms-graph2text","repo_kind":"official","path":"agenda/utils_graph2text.py","file_url":"https://github.com/UKPLab/plms-graph2text/blob/HEAD/agenda/utils_graph2text.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"16c9346aec54122b"}},{"code_sha256_prefix":"c246a8900dfb38bb","entry":"eval_meteor_test_webnlg","repo":"UKPLab/plms-graph2text","repo_kind":"official","path":"agenda/utils_graph2text.py","file_url":"https://github.com/UKPLab/plms-graph2text/blob/HEAD/agenda/utils_graph2text.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c246a8900dfb38bb"}},{"code_sha256_prefix":"01cc9caede179564","entry":"get_checkpoint_callback","repo":"UKPLab/plms-graph2text","repo_kind":"official","path":"agenda/callbacks.py","file_url":"https://github.com/UKPLab/plms-graph2text/blob/HEAD/agenda/callbacks.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"01cc9caede179564"}},{"code_sha256_prefix":"e386d3a24af4d168","entry":"label_smoothed_nll_loss","repo":"UKPLab/plms-graph2text","repo_kind":"official","path":"agenda/utils.py","file_url":"https://github.com/UKPLab/plms-graph2text/blob/HEAD/agenda/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e386d3a24af4d168"}},{"code_sha256_prefix":"7c43af131a6f39a6","entry":"lmap","repo":"UKPLab/plms-graph2text","repo_kind":"official","path":"agenda/utils.py","file_url":"https://github.com/UKPLab/plms-graph2text/blob/HEAD/agenda/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7c43af131a6f39a6"}},{"code_sha256_prefix":"c8825db3ade9d2ec","entry":"open_file","repo":"UKPLab/plms-graph2text","repo_kind":"official","path":"amr/comp_sacrebleu.py","file_url":"https://github.com/UKPLab/plms-graph2text/blob/HEAD/amr/comp_sacrebleu.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c8825db3ade9d2ec"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}