{"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/structural-information-preserving-for-graph-1","title":"Structural Information Preserving for Graph-to-Text Generation","arxiv_id":"2102.06749","date":"2021-02-12","proceeding":"ACL 2020 6","authors":["Linfeng Song","Ante Wang","Jinsong Su","Yue Zhang","Kun Xu","Yubin Ge","Dong Yu"],"abstract":"The task of graph-to-text generation aims at producing sentences that preserve the meaning of input graphs. As a crucial defect, the current state-of-the-art models may mess up or even drop the core structural information of input graphs when generating outputs. We propose to tackle this problem by leveraging richer training signals that can guide our model for preserving input information. In particular, we introduce two types of autoencoding losses, each individually focusing on different aspects (a.k.a. views) of input graphs. The losses are then back-propagated to better calibrate our model via multi-task training. Experiments on two benchmarks for graph-to-text generation show the effectiveness of our approach over a state-of-the-art baseline. Our code is available at \\url{http://github.com/Soistesimmer/AMR-multiview}.","url_abs":"https://arxiv.org/abs/2102.06749v1","url_pdf":"https://arxiv.org/pdf/2102.06749v1.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":"structural-information-preserving-for-graph-1","repo_url":"https://github.com/Soistesimmer/AMR-multiview","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"data-to-text-generation","task_name":"Data-to-Text Generation"},{"task_slug":"text-generation","task_name":"Text Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/data-to-text-generation-on-webnlg","task":"Data-to-Text Generation","dataset":"WebNLG","model":"Multiview-G2S","rank_in_archive_order":14,"of":20,"metrics":{"BLEU":"62.89"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2102.06749","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}