{"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/political-speech-generation","title":"Political Speech Generation","arxiv_id":"1601.03313","date":"2016-01-13","proceeding":null,"authors":["Valentin Kassarnig"],"abstract":"In this report we present a system that can generate political speeches for a\ndesired political party. Furthermore, the system allows to specify whether a\nspeech should hold a supportive or opposing opinion. The system relies on a\ncombination of several state-of-the-art NLP methods which are discussed in this\nreport. These include n-grams, Justeson & Katz POS tag filter, recurrent neural\nnetworks, and latent Dirichlet allocation. Sequences of words are generated\nbased on probabilities obtained from two underlying models: A language model\ntakes care of the grammatical correctness while a topic model aims for textual\nconsistency. Both models were trained on the Convote dataset which contains\ntranscripts from US congressional floor debates. Furthermore, we present a\nmanual and an automated approach to evaluate the quality of generated speeches.\nIn an experimental evaluation generated speeches have shown very high quality\nin terms of grammatical correctness and sentence transitions.","url_abs":"http://arxiv.org/abs/1601.03313v2","url_pdf":"http://arxiv.org/pdf/1601.03313v2.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":"political-speech-generation","repo_url":"https://github.com/valentin012/conspeech","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"political-speech-generation","repo_url":"https://github.com/ucsd-dsc-arts/dsc160-final-dsc160_final_group8","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"pos","task_name":"POS"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"tag","task_name":"TAG"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}