{"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/steering-output-style-and-topic-in-neural","title":"Steering Output Style and Topic in Neural Response Generation","arxiv_id":"1709.03010","date":"2017-09-09","proceeding":"EMNLP 2017 9","authors":["Di Wang","Nebojsa Jojic","Chris Brockett","Eric Nyberg"],"abstract":"We propose simple and flexible training and decoding methods for influencing\noutput style and topic in neural encoder-decoder based language generation.\nThis capability is desirable in a variety of applications, including\nconversational systems, where successful agents need to produce language in a\nspecific style and generate responses steered by a human puppeteer or external\nknowledge. We decompose the neural generation process into empirically easier\nsub-problems: a faithfulness model and a decoding method based on\nselective-sampling. We also describe training and sampling algorithms that bias\nthe generation process with a specific language style restriction, or a topic\nrestriction. Human evaluation results show that our proposed methods are able\nto restrict style and topic without degrading output quality in conversational\ntasks.","url_abs":"http://arxiv.org/abs/1709.03010v1","url_pdf":"http://arxiv.org/pdf/1709.03010v1.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":"steering-output-style-and-topic-in-neural","repo_url":"https://github.com/digo/steering-response-style-and-topic","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"response-generation","task_name":"Response Generation"},{"task_slug":"text-generation","task_name":"Text Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1709.03010","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}