CLApr 17, 2021

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

arXiv:2104.08481v1654 citations
Originality Incremental advance
AI Analysis

This work addresses the realistic scenario of few-shot learning for relation classification, focusing on handling unseen categories, but it is incremental as it builds on existing embedding-based approaches.

The authors tackled the problem of few-shot relation classification by highlighting unrealistic data distributions in existing benchmarks and proposing a new methodology to create a more challenging test set from TACRED, where state-of-the-art models performed poorly. They also introduced a novel classification scheme using learned vectors for the 'none-of-the-above' category, which showed empirical appeal.

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, aka 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 for supervised RC, and apply it to 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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes