Curriculum-Meta Learning for Order-Robust Continual Relation Extraction

Continual relation extraction is an important task that focuses on extracting new facts incrementally from unstructured text. Given the sequential arrival order of the relations, this task is prone to two serious challenges, namely catastrophic forgetting and order-sensitivity. We propose a novel curriculummeta learning method to tackle the above two challenges in continual relation extraction. We combine meta learning and curriculum learning to quickly adapt model parameters to a new task and to reduce interference of previously seen tasks on the current task. We design a novel relation representation learning method through the distribution of domain and range types of relations. Such representations are utilized to quantify the difficulty of tasks for the construction of curricula. Moreover, we also present novel difficultybased metrics to quantitatively measure the extent of ordersensitivity of a given model, suggesting new ways to evaluate model robustness. Our comprehensive experiments on three benchmark datasets show that our proposed method outperforms the state-of-the-art techniques. The code is available at https: //github. com/wutong8023/AAAI-CML.

Authors

• Tongtong Wu Southeast University School of Computer Science and Engineering
• Xuekai Li
• Yuan-Fang Li Monash University
• Gholamreza Haffari
• Guilin Qi School of Computer Science and Engineering, Southeast University, China State Key Laboratory for Novel Software Technology, Nanjing University, China
• Yujin Zhu
• Guoqiang Xu

Keywords

No keywords are indexed for this paper.