{"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/hierarchical-text-generation-and-planning-for","title":"Hierarchical Text Generation and Planning for Strategic Dialogue","arxiv_id":"1712.05846","date":"2017-12-15","proceeding":"ICML 2018 7","authors":["Denis Yarats","Mike Lewis"],"abstract":"End-to-end models for goal-orientated dialogue are challenging to train,\nbecause linguistic and strategic aspects are entangled in latent state vectors.\nWe introduce an approach to learning representations of messages in dialogues\nby maximizing the likelihood of subsequent sentences and actions, which\ndecouples the semantics of the dialogue utterance from its linguistic\nrealization. We then use these latent sentence representations for hierarchical\nlanguage generation, planning and reinforcement learning. Experiments show that\nour approach increases the end-task reward achieved by the model, improves the\neffectiveness of long-term planning using rollouts, and allows self-play\nreinforcement learning to improve decision making without diverging from human\nlanguage. Our hierarchical latent-variable model outperforms previous work both\nlinguistically and strategically.","url_abs":"http://arxiv.org/abs/1712.05846v2","url_pdf":"http://arxiv.org/pdf/1712.05846v2.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":"hierarchical-text-generation-and-planning-for","repo_url":"https://github.com/facebookresearch/end-to-end-negotiator","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"decision-making","task_name":"Decision Making"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"text-generation","task_name":"Text Generation"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[{"slug":"negotiation-dialogues-dataset","name":"Negotiation Dialogues Dataset","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1712.05846","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}