Continual Relation Extraction
Related Papers
Refining Sample Embeddings with Relation Prototypes to Enhance Continual Relation Extraction
AbstractContinual learning has gained increasing attention in recent years, thanks to its biological interpretation and efficiency in many real-world applications. As a typical task of continual learning, continual relation extraction …...
Consistent Representation Learning for Continual Relation Extraction
AbstractContinual relation extraction (CRE) aims to continuously train a model on data with new relations while avoiding forgetting old ones. Some previous work has proved that storing a few typical …...
Improving Continual Relation Extraction through Prototypical Contrastive Learning
AbstractContinual relation extraction (CRE) aims to extract relations towards the continuous and iterative arrival of new data, of which the major challenge is the catastrophic forgetting of old tasks. In …...
Learning Robust Representations for Continual Relation Extraction via Adversarial Class Augmentation
AbstractContinual relation extraction (CRE) aims to continually learn new relations from a class-incremental data stream. CRE model usually suffers from catastrophic forgetting problem, i.e., the performance of old relations seriously …...
Improving Continual Relation Extraction by Distinguishing Analogous Semantics
AbstractContinual relation extraction (RE) aims to learn constantly emerging relations while avoiding forgetting the learned relations. Existing works store a small number of typical samples to re-train the model for …...