{"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/discourse-embellishment-using-a-deep-encoder","title":"Discourse Embellishment Using a Deep Encoder-Decoder Network","arxiv_id":"1810.08076","date":"2018-10-18","proceeding":"WS 2018 11","authors":["Leonid Berov","Kai Standvoss"],"abstract":"We suggest a new NLG task in the context of the discourse generation pipeline\nof computational storytelling systems. This task, textual embellishment, is\ndefined by taking a text as input and generating a semantically equivalent\noutput with increased lexical and syntactic complexity. Ideally, this would\nallow the authors of computational storytellers to implement just lightweight\nNLG systems and use a domain-independent embellishment module to translate its\noutput into more literary text. We present promising first results on this task\nusing LSTM Encoder-Decoder networks trained on the WikiLarge dataset.\nFurthermore, we introduce \"Compiled Computer Tales\", a corpus of\ncomputationally generated stories, that can be used to test the capabilities of\nembellishment algorithms.","url_abs":"http://arxiv.org/abs/1810.08076v1","url_pdf":"http://arxiv.org/pdf/1810.08076v1.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":"discourse-embellishment-using-a-deep-encoder","repo_url":"https://github.com/cartisan/CompiledComputerTales","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"}],"methods":[{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}