Few-shot Continual Relation Extraction via Open Information Extraction
This work addresses the challenge of adapting relation extraction models to new tasks with limited data while retaining prior knowledge, which is incremental as it builds on existing FCRE methods by incorporating open information extraction concepts.
The paper tackles the problem of few-shot continual relation extraction by proposing a method that leverages open information extraction and knowledge graph construction to handle unseen or undetermined relations, resulting in superior performance compared to state-of-the-art baselines and efficient dynamic graph construction.
Typically, Few-shot Continual Relation Extraction (FCRE) models must balance retaining prior knowledge while adapting to new tasks with extremely limited data. However, real-world scenarios may also involve unseen or undetermined relations that existing methods still struggle to handle. To address these challenges, we propose a novel approach that leverages the Open Information Extraction concept of Knowledge Graph Construction (KGC). Our method not only exposes models to all possible pairs of relations, including determined and undetermined labels not available in the training set, but also enriches model knowledge with diverse relation descriptions, thereby enhancing knowledge retention and adaptability in this challenging scenario. In the perspective of KGC, this is the first work explored in the setting of Continual Learning, allowing efficient expansion of the graph as the data evolves. Experimental results demonstrate our superior performance compared to other state-of-the-art FCRE baselines, as well as the efficiency in handling dynamic graph construction in this setting.