{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/jointgt-graph-text-joint-representation","title":"JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge Graphs","arxiv_id":"2106.10502","date":"2021-06-19","proceeding":"Findings (ACL) 2021 8","authors":["Pei Ke","Haozhe Ji","Yu Ran","Xin Cui","LiWei Wang","Linfeng Song","Xiaoyan Zhu","Minlie Huang"],"abstract":"Existing pre-trained models for knowledge-graph-to-text (KG-to-text) generation simply fine-tune text-to-text pre-trained models such as BART or T5 on KG-to-text datasets, which largely ignore the graph structure during encoding and lack elaborate pre-training tasks to explicitly model graph-text alignments. To tackle these problems, we propose a graph-text joint representation learning model called JointGT. During encoding, we devise a structure-aware semantic aggregation module which is plugged into each Transformer layer to preserve the graph structure. Furthermore, we propose three new pre-training tasks to explicitly enhance the graph-text alignment including respective text / graph reconstruction, and graph-text alignment in the embedding space via Optimal Transport. Experiments show that JointGT obtains new state-of-the-art performance on various KG-to-text datasets.","url_abs":"https://arxiv.org/abs/2106.10502v1","url_pdf":"https://arxiv.org/pdf/2106.10502v1.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":"jointgt-graph-text-joint-representation","repo_url":"https://github.com/thu-coai/JointGT","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"graph-reconstruction","task_name":"Graph Reconstruction"},{"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":"representation-learning","task_name":"Representation Learning"},{"task_slug":"text-generation","task_name":"Text Generation"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"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":"label-smoothing","method_name":"Label Smoothing"},{"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":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"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"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/kg-to-text-generation-on-pathquestion","task":"KG-to-Text Generation","dataset":"PathQuestion","model":"JointGT (BART)","rank_in_archive_order":1,"of":5,"metrics":{"BLEU":"65.89","METEOR":"48.25","ROUGE":"78.87"},"uses_additional_data":false},{"leaderboard":"/sota/kg-to-text-generation-on-pathquestion","task":"KG-to-Text Generation","dataset":"PathQuestion","model":"BART","rank_in_archive_order":2,"of":5,"metrics":{"BLEU":"63.74","METEOR":"47.23","ROUGE":"77.76"},"uses_additional_data":false},{"leaderboard":"/sota/kg-to-text-generation-on-pathquestion","task":"KG-to-Text Generation","dataset":"PathQuestion","model":"JointGT (T5)","rank_in_archive_order":4,"of":5,"metrics":{"BLEU":"60.45","METEOR":"45.38","ROUGE":"77.59"},"uses_additional_data":false},{"leaderboard":"/sota/kg-to-text-generation-on-pathquestion","task":"KG-to-Text Generation","dataset":"PathQuestion","model":"T5","rank_in_archive_order":5,"of":5,"metrics":{"BLEU":"58.95","METEOR":"44.72","ROUGE":"76.58"},"uses_additional_data":false},{"leaderboard":"/sota/kg-to-text-generation-on-webnlg-2-0-1","task":"KG-to-Text Generation","dataset":"WebNLG 2.0 (Constrained)","model":"JointGT (T5)","rank_in_archive_order":5,"of":9,"metrics":{"BLEU":"61.01","METEOR":"46.32","ROUGE":"73.57"},"uses_additional_data":false},{"leaderboard":"/sota/kg-to-text-generation-on-webnlg-2-0-1","task":"KG-to-Text Generation","dataset":"WebNLG 2.0 (Constrained)","model":"T5","rank_in_archive_order":6,"of":9,"metrics":{"BLEU":"58.66","METEOR":"46.04","ROUGE":"73.06"},"uses_additional_data":false},{"leaderboard":"/sota/kg-to-text-generation-on-webnlg-2-0-1","task":"KG-to-Text Generation","dataset":"WebNLG 2.0 (Constrained)","model":"JointGT (BART)","rank_in_archive_order":7,"of":9,"metrics":{"BLEU":"58.55","METEOR":"45.01","ROUGE":"72.31"},"uses_additional_data":false},{"leaderboard":"/sota/kg-to-text-generation-on-webnlg-2-0-1","task":"KG-to-Text Generation","dataset":"WebNLG 2.0 (Constrained)","model":"BART","rank_in_archive_order":8,"of":9,"metrics":{"BLEU":"56.65","METEOR":"44.51","ROUGE":"70.94"},"uses_additional_data":false},{"leaderboard":"/sota/kg-to-text-generation-on-webnlg-2-0","task":"KG-to-Text Generation","dataset":"WebNLG 2.0 (Unconstrained)","model":"JointGT (T5)","rank_in_archive_order":2,"of":13,"metrics":{"BLEU":"66.14","METEOR":"47.25","ROUGE":"75.91"},"uses_additional_data":false},{"leaderboard":"/sota/kg-to-text-generation-on-webnlg-2-0","task":"KG-to-Text Generation","dataset":"WebNLG 2.0 (Unconstrained)","model":"JointGT (BART)","rank_in_archive_order":3,"of":13,"metrics":{"BLEU":"65.92","METEOR":"47.15","ROUGE":"76.10"},"uses_additional_data":false},{"leaderboard":"/sota/kg-to-text-generation-on-webnlg-2-0","task":"KG-to-Text Generation","dataset":"WebNLG 2.0 (Unconstrained)","model":"BART","rank_in_archive_order":6,"of":13,"metrics":{"BLEU":"64.55","METEOR":"46.51","ROUGE":"75.13"},"uses_additional_data":false},{"leaderboard":"/sota/kg-to-text-generation-on-webnlg-2-0","task":"KG-to-Text Generation","dataset":"WebNLG 2.0 (Unconstrained)","model":"T5","rank_in_archive_order":7,"of":13,"metrics":{"BLEU":"64.42","METEOR":"46.58","ROUGE":"74.77"},"uses_additional_data":false},{"leaderboard":"/sota/kg-to-text-generation-on-webquestions","task":"KG-to-Text Generation","dataset":"WebQuestions","model":"JointGT (BART)","rank_in_archive_order":1,"of":5,"metrics":{"BLEU":"30.02","METEOR":"32.05","ROUGE":"55.6"},"uses_additional_data":false},{"leaderboard":"/sota/kg-to-text-generation-on-webquestions","task":"KG-to-Text Generation","dataset":"WebQuestions","model":"BART","rank_in_archive_order":2,"of":5,"metrics":{"BLEU":"29.61","METEOR":"31.48","ROUGE":"55.42"},"uses_additional_data":false},{"leaderboard":"/sota/kg-to-text-generation-on-webquestions","task":"KG-to-Text Generation","dataset":"WebQuestions","model":"JointGT (T5)","rank_in_archive_order":4,"of":5,"metrics":{"BLEU":"28.95","METEOR":"31.29","ROUGE":"54.47"},"uses_additional_data":false},{"leaderboard":"/sota/kg-to-text-generation-on-webquestions","task":"KG-to-Text Generation","dataset":"WebQuestions","model":"T5","rank_in_archive_order":5,"of":5,"metrics":{"BLEU":"28.78","METEOR":"30.55","ROUGE":"55.12"},"uses_additional_data":false},{"leaderboard":"/sota/question-generation-on-grailqa-compositional","task":"Question Generation","dataset":"GrailQA-Compositional","model":"JointGT","rank_in_archive_order":2,"of":4,"metrics":{"BLEU":"31.46","FactSpotter":"95.26","METEOR":"36.08"},"uses_additional_data":false},{"leaderboard":"/sota/question-generation-on-grailqa-iid","task":"Question Generation","dataset":"GrailQA-IID","model":"JointGT","rank_in_archive_order":2,"of":4,"metrics":{"BLEU":"45.95","FactSpotter":"98.62","METEOR":"41.65"},"uses_additional_data":false},{"leaderboard":"/sota/question-generation-on-grailqa-zero-shot","task":"Question Generation","dataset":"GrailQA-Zero-Shot","model":"JointGT","rank_in_archive_order":1,"of":4,"metrics":{"FactSpotter":"94.15","METEOR":"37.69","bleu":"32.94"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2106.10502","atlas_url":"https://app.syntology.ai/?focus=2106.10502","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2106.10502"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2106.10502\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2106.10502"},"call":"get_concepts_for_paper(arxiv_id=\"2106.10502\")"}],"by_repo":[{"repo":"thu-coai/JointGT","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"3182f92f839c2121d245af010573bd1c7fa79d3b78543a2c1fdda2e313248fd7","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}