{"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-intention-dialogue-models","title":"Latent Intention Dialogue Models","arxiv_id":"1705.10229","date":"2017-05-29","proceeding":"ICML 2017 8","authors":["Tsung-Hsien Wen","Yishu Miao","Phil Blunsom","Steve Young"],"abstract":"Developing a dialogue agent that is capable of making autonomous decisions\nand communicating by natural language is one of the long-term goals of machine\nlearning research. Traditional approaches either rely on hand-crafting a small\nstate-action set for applying reinforcement learning that is not scalable or\nconstructing deterministic models for learning dialogue sentences that fail to\ncapture natural conversational variability. In this paper, we propose a Latent\nIntention Dialogue Model (LIDM) that employs a discrete latent variable to\nlearn underlying dialogue intentions in the framework of neural variational\ninference. In a goal-oriented dialogue scenario, these latent intentions can be\ninterpreted as actions guiding the generation of machine responses, which can\nbe further refined autonomously by reinforcement learning. The experimental\nevaluation of LIDM shows that the model out-performs published benchmarks for\nboth corpus-based and human evaluation, demonstrating the effectiveness of\ndiscrete latent variable models for learning goal-oriented dialogues.","url_abs":"http://arxiv.org/abs/1705.10229v1","url_pdf":"http://arxiv.org/pdf/1705.10229v1.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-intention-dialogue-models","repo_url":"https://github.com/shawnwun/NNDIAL","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"variational-inference","task_name":"Variational Inference"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1705.10229","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}