{"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/stage-wise-fine-tuning-for-graph-to-text","title":"Stage-wise Fine-tuning for Graph-to-Text Generation","arxiv_id":"2105.08021","date":"2021-05-17","proceeding":"ACL 2021 5","authors":["Qingyun Wang","Semih Yavuz","Victoria Lin","Heng Ji","Nazneen Rajani"],"abstract":"Graph-to-text generation has benefited from pre-trained language models (PLMs) in achieving better performance than structured graph encoders. However, they fail to fully utilize the structure information of the input graph. In this paper, we aim to further improve the performance of the pre-trained language model by proposing a structured graph-to-text model with a two-step fine-tuning mechanism which first fine-tunes the model on Wikipedia before adapting to the graph-to-text generation. In addition to using the traditional token and position embeddings to encode the knowledge graph (KG), we propose a novel tree-level embedding method to capture the inter-dependency structures of the input graph. This new approach has significantly improved the performance of all text generation metrics for the English WebNLG 2017 dataset.","url_abs":"https://arxiv.org/abs/2105.08021v2","url_pdf":"https://arxiv.org/pdf/2105.08021v2.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":"stage-wise-fine-tuning-for-graph-to-text","repo_url":"https://github.com/EagleW/Stage-wise-Fine-tuning","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"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":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":null,"task_name":"Position"},{"task_slug":"text-generation","task_name":"Text Generation"}],"methods":[{"method_slug":"adafactor","method_name":"Adafactor"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"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-large + Wiki + Position","rank_in_archive_order":7,"of":20,"metrics":{"BLEU":"66.07"},"uses_additional_data":true},{"leaderboard":"/sota/data-to-text-generation-on-webnlg-full-1","task":"Data-to-Text Generation","dataset":"WebNLG Full","model":"T5-large + Wiki + Position","rank_in_archive_order":3,"of":8,"metrics":{"BLEU":"60.56"},"uses_additional_data":true}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2105.08021","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}