{"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/step-by-step-separating-planning-from","title":"Step-by-Step: Separating Planning from Realization in Neural Data-to-Text Generation","arxiv_id":"1904.03396","date":"2019-04-06","proceeding":"NAACL 2019 6","authors":["Amit Moryossef","Yoav Goldberg","Ido Dagan"],"abstract":"Data-to-text generation can be conceptually divided into two parts: ordering\nand structuring the information (planning), and generating fluent language\ndescribing the information (realization). Modern neural generation systems\nconflate these two steps into a single end-to-end differentiable system. We\npropose to split the generation process into a symbolic text-planning stage\nthat is faithful to the input, followed by a neural generation stage that\nfocuses only on realization. For training a plan-to-text generator, we present\na method for matching reference texts to their corresponding text plans. For\ninference time, we describe a method for selecting high-quality text plans for\nnew inputs. We implement and evaluate our approach on the WebNLG benchmark. Our\nresults demonstrate that decoupling text planning from neural realization\nindeed improves the system's reliability and adequacy while maintaining fluent\noutput. We observe improvements both in BLEU scores and in manual evaluations.\nAnother benefit of our approach is the ability to output diverse realizations\nof the same input, paving the way to explicit control over the generated text\nstructure.","url_abs":"http://arxiv.org/abs/1904.03396v2","url_pdf":"http://arxiv.org/pdf/1904.03396v2.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":"step-by-step-separating-planning-from","repo_url":"https://github.com/AmitMY/chimera","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"data-to-text-generation","task_name":"Data-to-Text Generation"},{"task_slug":"graph-to-sequence","task_name":"Graph-to-Sequence"},{"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":"BestPlan","rank_in_archive_order":19,"of":20,"metrics":{"BLEU":"47.4"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1904.03396","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.03396"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/AmitMY/chimera","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":5},"by_repo_kind":{"official":{"samples":5,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"3244d82a578f81d9","entry":"add_features","repo":"AmitMY/chimera","repo_kind":"official","path":"model/model_runner.py","file_url":"https://github.com/AmitMY/chimera/blob/HEAD/model/model_runner.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3244d82a578f81d9"}},{"code_sha256_prefix":"bd409aa14888675e","entry":"arg_sample","repo":"AmitMY/chimera","repo_kind":"official","path":"utils/dynet_model_executer.py","file_url":"https://github.com/AmitMY/chimera/blob/HEAD/utils/dynet_model_executer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bd409aa14888675e"}},{"code_sha256_prefix":"546ed64d4d32a793","entry":"get_entities","repo":"AmitMY/chimera","repo_kind":"official","path":"model/open_nmt.py","file_url":"https://github.com/AmitMY/chimera/blob/HEAD/model/open_nmt.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"546ed64d4d32a793"}},{"code_sha256_prefix":"52464ce51f9e6041","entry":"get_relations","repo":"AmitMY/chimera","repo_kind":"official","path":"scorer/scorer.py","file_url":"https://github.com/AmitMY/chimera/blob/HEAD/scorer/scorer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"52464ce51f9e6041"}},{"code_sha256_prefix":"7aa83b9a9ebacd43","entry":"spread_translation_dict","repo":"AmitMY/chimera","repo_kind":"official","path":"model/model_runner.py","file_url":"https://github.com/AmitMY/chimera/blob/HEAD/model/model_runner.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7aa83b9a9ebacd43"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}