{"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/data-to-text-generation-with-variational","title":"Data-to-text Generation with Variational Sequential Planning","arxiv_id":"2202.13756","date":"2022-02-28","proceeding":null,"authors":["Ratish Puduppully","Yao Fu","Mirella Lapata"],"abstract":"We consider the task of data-to-text generation, which aims to create textual output from non-linguistic input. We focus on generating long-form text, i.e., documents with multiple paragraphs, and propose a neural model enhanced with a planning component responsible for organizing high-level information in a coherent and meaningful way. We infer latent plans sequentially with a structured variational model, while interleaving the steps of planning and generation. Text is generated by conditioning on previous variational decisions and previously generated text. Experiments on two data-to-text benchmarks (RotoWire and MLB) show that our model outperforms strong baselines and is sample efficient in the face of limited training data (e.g., a few hundred instances).","url_abs":"https://arxiv.org/abs/2202.13756v1","url_pdf":"https://arxiv.org/pdf/2202.13756v1.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":"data-to-text-generation-with-variational","repo_url":"https://github.com/ratishsp/data2text-seq-plan-py","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":"text-generation","task_name":"Text Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/data-to-text-generation-on-mlb-dataset-2","task":"Data-to-Text Generation","dataset":"MLB Dataset","model":"SeqPlan","rank_in_archive_order":1,"of":4,"metrics":{"BLEU":"14.29"},"uses_additional_data":false},{"leaderboard":"/sota/data-to-text-generation-on-mlb-dataset-3","task":"Data-to-Text Generation","dataset":"MLB Dataset (Content Ordering)","model":"SeqPlan","rank_in_archive_order":1,"of":4,"metrics":{"DLD":"22.7"},"uses_additional_data":false},{"leaderboard":"/sota/data-to-text-generation-on-mlb-dataset-1","task":"Data-to-Text Generation","dataset":"MLB Dataset (Content Selection)","model":"SeqPlan","rank_in_archive_order":2,"of":3,"metrics":{"Precision":"43.3","Recall":"53.5"},"uses_additional_data":false},{"leaderboard":"/sota/data-to-text-generation-on-mlb-dataset","task":"Data-to-Text Generation","dataset":"MLB Dataset (Relation Generation)","model":"SeqPlan","rank_in_archive_order":1,"of":4,"metrics":{"Precision":"95.9","count":"28.9"},"uses_additional_data":false},{"leaderboard":"/sota/data-to-text-generation-on-rotowire-relation","task":"Data-to-Text Generation","dataset":"RotoWire (Relation Generation)","model":"SeqPlan","rank_in_archive_order":1,"of":6,"metrics":{"Precision":"97.6","count":"46.7"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2202.13756","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}