Revisiting Few-shot Relation Classification: Evaluation Data and Classification Schemes

Revisiting Few-shot Relation Classification: Evaluation Data and Classification Schemes

Blog Article

We explore few-shot learning (FSL) for relation classification (RC).Focusing on the realistic scenario of FSL, in which a test instance might not belong to any of the target categories (none-of-the-above, [NOTA]), we first revisit the recent popular dataset structure for FSL, pointing out its unrealistic data distribution.To remedy this, we propose a novel methodology for deriving more realistic few-shot test data from available datasets ivoryjinelle.com for supervised RC, and apply it to southwestern aztec rug the TACRED dataset.This yields a new challenging benchmark for FSL-RC, on which state of the art models show poor performance.Next, we analyze classification schemes within the popular embedding-based nearest-neighbor approach for FSL, with respect to constraints they impose on the embedding space.

Triggered by this analysis, we propose a novel classification scheme in which the NOTA category is represented as learned vectors, shown empirically to be an appealing option for FSL.