{"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/unsupervised-natural-language-generation-with","title":"Unsupervised Natural Language Generation with Denoising Autoencoders","arxiv_id":"1804.07899","date":"2018-04-21","proceeding":"EMNLP 2018 10","authors":["Markus Freitag","Scott Roy"],"abstract":"Generating text from structured data is important for various tasks such as\nquestion answering and dialog systems. We show that in at least one domain,\nwithout any supervision and only based on unlabeled text, we are able to build\na Natural Language Generation (NLG) system with higher performance than\nsupervised approaches. In our approach, we interpret the structured data as a\ncorrupt representation of the desired output and use a denoising auto-encoder\nto reconstruct the sentence. We show how to introduce noise into training\nexamples that do not contain structured data, and that the resulting denoising\nauto-encoder generalizes to generate correct sentences when given structured\ndata.","url_abs":"http://arxiv.org/abs/1804.07899v2","url_pdf":"http://arxiv.org/pdf/1804.07899v2.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":"unsupervised-natural-language-generation-with","repo_url":"https://github.com/mcleonard/NLG_Autoencoder","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"text-generation","task_name":"Text Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1804.07899","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1804.07899"}},"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/mcleonard/NLG_Autoencoder","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":3},"by_repo_kind":{"listed":{"samples":3,"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":"3c0f71922f1902b5","entry":"corrupt","repo":"mcleonard/NLG_Autoencoder","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/mcleonard/NLG_Autoencoder/blob/HEAD/utils.py","link_basis":"harvester_set","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":"3c0f71922f1902b5"}},{"code_sha256_prefix":"4c8c8dc9b74f932e","entry":"extract_ngrams","repo":"mcleonard/NLG_Autoencoder","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/mcleonard/NLG_Autoencoder/blob/HEAD/utils.py","link_basis":"harvester_set","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":"4c8c8dc9b74f932e"}},{"code_sha256_prefix":"7f748724eeba5ef7","entry":"replace_punctuation","repo":"mcleonard/NLG_Autoencoder","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/mcleonard/NLG_Autoencoder/blob/HEAD/utils.py","link_basis":"harvester_set","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":"7f748724eeba5ef7"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}