{"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/ask-question-first-for-enhancing-lifelong","title":"Ask Question First for Enhancing Lifelong Language Learning","arxiv_id":"2208.08367","date":"2022-08-17","proceeding":"COLING 2022 10","authors":["Han Wang","Ruiliu Fu","Xuejun Zhang","Jun Zhou","Qingwei Zhao"],"abstract":"Lifelong language learning aims to stream learning NLP tasks while retaining knowledge of previous tasks. Previous works based on the language model and following data-free constraint approaches have explored formatting all data as \"begin token (\\textit{B}) + context (\\textit{C}) + question (\\textit{Q}) + answer (\\textit{A})\" for different tasks. However, they still suffer from catastrophic forgetting and are exacerbated when the previous task's pseudo data is insufficient for the following reasons: (1) The model has difficulty generating task-corresponding pseudo data, and (2) \\textit{A} is prone to error when \\textit{A} and \\textit{C} are separated by \\textit{Q} because the information of the \\textit{C} is diminished before generating \\textit{A}. Therefore, we propose the Ask Question First and Replay Question (AQF-RQ), including a novel data format \"\\textit{BQCA}\" and a new training task to train pseudo questions of previous tasks. Experimental results demonstrate that AQF-RQ makes it easier for the model to generate more pseudo data that match corresponding tasks, and is more robust to both sufficient and insufficient pseudo-data when the task boundary is both clear and unclear. AQF-RQ can achieve only 0.36\\% lower performance than multi-task learning.","url_abs":"https://arxiv.org/abs/2208.08367v2","url_pdf":"https://arxiv.org/pdf/2208.08367v2.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":"ask-question-first-for-enhancing-lifelong","repo_url":"https://github.com/codehan/aqf-rq","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"multi-task-learning","task_name":"Multi-Task Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}