{"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/a-hierarchical-model-for-data-to-text","title":"A Hierarchical Model for Data-to-Text Generation","arxiv_id":"1912.10011","date":"2019-12-20","proceeding":null,"authors":["Clément Rebuffel","Laure Soulier","Geoffrey Scoutheeten","Patrick Gallinari"],"abstract":"Transcribing structured data into natural language descriptions has emerged as a challenging task, referred to as \"data-to-text\". These structures generally regroup multiple elements, as well as their attributes. Most attempts rely on translation encoder-decoder methods which linearize elements into a sequence. This however loses most of the structure contained in the data. In this work, we propose to overpass this limitation with a hierarchical model that encodes the data-structure at the element-level and the structure level. Evaluations on RotoWire show the effectiveness of our model w.r.t. qualitative and quantitative metrics.","url_abs":"https://arxiv.org/abs/1912.10011v1","url_pdf":"https://arxiv.org/pdf/1912.10011v1.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":"a-hierarchical-model-for-data-to-text","repo_url":"https://github.com/KaijuML/data-to-text-hierarchical","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":"decoder","task_name":"Decoder"},{"task_slug":"text-generation","task_name":"Text Generation"},{"task_slug":"translation","task_name":"Translation"},{"task_slug":"model","task_name":"model"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/data-to-text-generation-on-rotowire","task":"Data-to-Text Generation","dataset":"RotoWire","model":"Hierarchical transformer encoder + conditional copy","rank_in_archive_order":2,"of":6,"metrics":{"BLEU":"17.50"},"uses_additional_data":false},{"leaderboard":"/sota/data-to-text-generation-on-rotowire-content","task":"Data-to-Text Generation","dataset":"RotoWire (Content Ordering)","model":"Hierarchical Transformer Encoder + conditional copy","rank_in_archive_order":1,"of":5,"metrics":{"BLEU":"17.50","DLD":"18.90%"},"uses_additional_data":false},{"leaderboard":"/sota/data-to-text-generation-on-rotowire-relation","task":"Data-to-Text Generation","dataset":"RotoWire (Relation Generation)","model":"Hierarchical Transformer Encoder +  conditional copy","rank_in_archive_order":4,"of":6,"metrics":{"Precision":"89.46%","count":"21.17"},"uses_additional_data":false},{"leaderboard":"/sota/data-to-text-generation-on-rotowire-content-1","task":"Data-to-Text Generation","dataset":"Rotowire (Content Selection)","model":"Hierarchical Transformer Encoder + conditional copy","rank_in_archive_order":1,"of":5,"metrics":{"Precision":"39.47%","Recall":"51.64%"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1912.10011","atlas_url":"https://app.syntology.ai/?focus=1912.10011","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}