{"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/continual-learning-in-task-oriented-dialogue","title":"Continual Learning in Task-Oriented Dialogue Systems","arxiv_id":"2012.15504","date":"2020-12-31","proceeding":"EMNLP 2021 11","authors":["Andrea Madotto","Zhaojiang Lin","Zhenpeng Zhou","Seungwhan Moon","Paul Crook","Bing Liu","Zhou Yu","Eunjoon Cho","Zhiguang Wang"],"abstract":"Continual learning in task-oriented dialogue systems can allow us to add new domains and functionalities through time without incurring the high cost of a whole system retraining. In this paper, we propose a continual learning benchmark for task-oriented dialogue systems with 37 domains to be learned continuously in four settings, such as intent recognition, state tracking, natural language generation, and end-to-end. Moreover, we implement and compare multiple existing continual learning baselines, and we propose a simple yet effective architectural method based on residual adapters. Our experiments demonstrate that the proposed architectural method and a simple replay-based strategy perform comparably well but they both achieve inferior performance to the multi-task learning baseline, in where all the data are shown at once, showing that continual learning in task-oriented dialogue systems is a challenging task. Furthermore, we reveal several trade-offs between different continual learning methods in term of parameter usage and memory size, which are important in the design of a task-oriented dialogue system. The proposed benchmark is released together with several baselines to promote more research in this direction.","url_abs":"https://arxiv.org/abs/2012.15504v1","url_pdf":"https://arxiv.org/pdf/2012.15504v1.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":"continual-learning-in-task-oriented-dialogue","repo_url":"https://github.com/andreamad8/ToDCL","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"continual-learning","task_name":"Continual Learning"},{"task_slug":"intent-recognition","task_name":"Intent Recognition"},{"task_slug":"multi-task-learning","task_name":"Multi-Task Learning"},{"task_slug":"task-oriented-dialogue-systems","task_name":"Task-Oriented Dialogue Systems"},{"task_slug":"text-generation","task_name":"Text Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2012.15504","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}