{"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/few-shot-generalization-across-dialogue-tasks","title":"Few-Shot Generalization Across Dialogue Tasks","arxiv_id":"1811.11707","date":"2018-11-28","proceeding":null,"authors":["Vladimir Vlasov","Akela Drissner-Schmid","Alan Nichol"],"abstract":"Machine-learning based dialogue managers are able to learn complex behaviors\nin order to complete a task, but it is not straightforward to extend their\ncapabilities to new domains. We investigate different policies' ability to\nhandle uncooperative user behavior, and how well expertise in completing one\ntask (such as restaurant reservations) can be reapplied when learning a new one\n(e.g. booking a hotel). We introduce the Recurrent Embedding Dialogue Policy\n(REDP), which embeds system actions and dialogue states in the same vector\nspace. REDP contains a memory component and attention mechanism based on a\nmodified Neural Turing Machine, and significantly outperforms a baseline LSTM\nclassifier on this task. We also show that both our architecture and baseline\nsolve the bAbI dialogue task, achieving 100% test accuracy.","url_abs":"http://arxiv.org/abs/1811.11707v1","url_pdf":"http://arxiv.org/pdf/1811.11707v1.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":"few-shot-generalization-across-dialogue-tasks","repo_url":"https://github.com/RasaHQ/conversational-ai-workshop-18","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"few-shot-generalization-across-dialogue-tasks","repo_url":"https://github.com/RasaHQ/rasa","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[],"methods":[{"method_slug":"content-based-attention","method_name":"Content-based Attention"},{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"location-based-attention","method_name":"Location-based Attention"},{"method_slug":"neural-turing-machine","method_name":"Neural Turing Machine"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1811.11707","atlas_url":"https://app.syntology.ai/?focus=1811.11707","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}