English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Continual relation extraction (CRE) requires the model to continually learnnew relations from class-incremental data streams. In this paper, we propose aFrustratingly easy but Effective Approach (FEA) method with two learning stagesfor CRE: 1) Fast Adaption (FA) warms up the model with only new data. 2)Balanced Tuning (BT) finetunes the model on the balanced memory data. Despiteits simplicity, FEA achieves comparable (on TACRED or superior (on FewRel)performance compared with the state-of-the-art baselines. With carefulexaminations, we find that the data imbalance between new and old relationsleads to a skewed decision boundary in the head classifiers over the pretrainedencoders, thus hurting the overall performance. In FEA, the FA stage unleashesthe potential of memory data for the subsequent finetuning, while the BT stagehelps establish a more balanced decision boundary. With a unified view, we findthat two strong CRE baselines can be subsumed into the proposed trainingpipeline. The success of FEA also provides actionable insights and suggestionsfor future model designing in CRE.

Less is More: Rethinking State-of-the-art Continual Relation Extraction Models with a Frustratingly Easy but Effective Approach