Distill and Replay for Continual Language Learning | |
Sun, Jingyuan3,4; Wang, Shaonan3,4; Zhang, Jiajun2,3,4; Zong, Chengqing1,3,4 | |
2020-12 | |
会议日期 | 2020-12-8 |
会议地点 | Barcelona, Spain (Online) |
英文摘要 | Accumulating knowledge to tackle new tasks without necessarily forgetting the old ones is a hallmark of human-like intelligence. But the current dominant paradigm of machine learning is still to train a model that works well on static datasets. When learning tasks in a stream where data distribution may fluctuate, fitting on new tasks often leads to forgetting on the previous ones. We propose a simple yet effective framework that continually learns natural language understanding tasks with one model. Our framework distills knowledge and replays experience from previous tasks when fitting on a new task, thus named DnR (distill and replay). The framework is based on language models and can be smoothly built with different language model architectures. Experimental results demonstrate that DnR outperfoms previous state-of-the-art models in continually learning tasks of the same type but from different domains, as well as tasks of radically different types. With the distillation method, we further show that it’s possible for DnR to incrementally compress the model size while still outperforming most of the baselines. We hope that DnR could promote the empirical application of continual language learning, and contribute to building human-level language intelligence minimally bothered by catastrophic forgetting. |
会议录出版者 | ACL |
语种 | 英语 |
内容类型 | 会议论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/45002] |
专题 | 模式识别国家重点实验室_自然语言处理 |
作者单位 | 1.CAS Center for Excellence in Brain Science and Intelligence Technology, China 2.Beijing Academy of Artificial Intelligence, Beijing, China 3.National Laboratory of Pattern Recognition, CASIA, Beijing, China 4.University of Chinese Academy of Sciences, Beijing, China |
推荐引用方式 GB/T 7714 | Sun, Jingyuan,Wang, Shaonan,Zhang, Jiajun,et al. Distill and Replay for Continual Language Learning[C]. 见:. Barcelona, Spain (Online). 2020-12-8. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论