自然语言处理任务的持续学习：综述
Continual Learning of Natural Language Processing Tasks: A Survey
AI总结：
本综述全面回顾了NLP中持续学习的最新进展，涵盖所有设置、灾难性遗忘预防、知识迁移及任务间类别分离挑战，并提出了未来研究方向。
摘要：
持续学习（CL）是一种学习范式，它模拟人类不断学习和积累知识的能力，同时不遗忘先前学到的知识，并将所学知识迁移以更好地帮助学习新任务。本综述全面回顾和分析了自然语言处理（NLP）中持续学习的最新进展，其与计算机视觉和机器学习中的持续学习存在显著差异。它涵盖了（1）所有持续学习设置，并提供了现有技术的分类；（2）灾难性遗忘（CF）的预防；（3）知识迁移（KT），这对NLP任务尤为重要；以及（4）一些理论和任务间类别分离（ICS）这一隐藏挑战。其中（1）、（3）和（4）未包含在现有综述中。最后，讨论了未来研究方向的一系列列表。
英文摘要：
Continual learning (CL) is a learning paradigm that emulates the human capability of learning and accumulating knowledge continually without forgetting the previously learned knowledge and also transferring the learned knowledge to help learn new tasks better. This survey presents a comprehensive review and analysis of the recent progress of CL in NLP, which has significant differences from CL in computer vision and machine learning. It covers (1) all CL settings with a taxonomy of existing techniques; (2) catastrophic forgetting (CF) prevention, (3) knowledge transfer (KT), which is particularly important for NLP tasks; and (4) some theory and the hidden challenge of inter-task class separation (ICS). (1), (3) and (4) have not been included in the existing survey. Finally, a list of future directions is discussed.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
