{"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/variational-cross-domain-natural-language","title":"Variational Cross-domain Natural Language Generation for Spoken Dialogue Systems","arxiv_id":"1812.08879","date":"2018-12-20","proceeding":"WS 2018 7","authors":["Bo-Hsiang Tseng","Florian Kreyssig","Pawel Budzianowski","Inigo Casanueva","Yen-chen Wu","Stefan Ultes","Milica Gasic"],"abstract":"Cross-domain natural language generation (NLG) is still a difficult task\nwithin spoken dialogue modelling. Given a semantic representation provided by\nthe dialogue manager, the language generator should generate sentences that\nconvey desired information. Traditional template-based generators can produce\nsentences with all necessary information, but these sentences are not\nsufficiently diverse. With RNN-based models, the diversity of the generated\nsentences can be high, however, in the process some information is lost. In\nthis work, we improve an RNN-based generator by considering latent information\nat the sentence level during generation using the conditional variational\nautoencoder architecture. We demonstrate that our model outperforms the\noriginal RNN-based generator, while yielding highly diverse sentences. In\naddition, our model performs better when the training data is limited.","url_abs":"http://arxiv.org/abs/1812.08879v1","url_pdf":"http://arxiv.org/pdf/1812.08879v1.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":"variational-cross-domain-natural-language","repo_url":"https://github.com/andy194673/nlg-scvae","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"spoken-dialogue-systems","task_name":"Spoken Dialogue Systems"},{"task_slug":"text-generation","task_name":"Text Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1812.08879","atlas_url":"https://app.syntology.ai/?focus=1812.08879","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}