{"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/latent-variable-dialogue-models-and-their","title":"Latent Variable Dialogue Models and their Diversity","arxiv_id":"1702.05962","date":"2017-02-20","proceeding":"EACL 2017 4","authors":["Kris Cao","Stephen Clark"],"abstract":"We present a dialogue generation model that directly captures the variability\nin possible responses to a given input, which reduces the `boring output' issue\nof deterministic dialogue models. Experiments show that our model generates\nmore diverse outputs than baseline models, and also generates more consistently\nacceptable output than sampling from a deterministic encoder-decoder model.","url_abs":"http://arxiv.org/abs/1702.05962v1","url_pdf":"http://arxiv.org/pdf/1702.05962v1.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":"latent-variable-dialogue-models-and-their","repo_url":"https://github.com/timbmg/DIAL-LV","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"dialogue-generation","task_name":"Dialogue Generation"},{"task_slug":"diversity","task_name":"Diversity"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1702.05962","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}