Learning to Decouple Relations: Few-Shot Relation Classification with Entity-Guided Attention and Confusion-Aware Training

TL;DR

This paper introduces CTEG, a novel model for few-shot relation classification that uses entity-guided attention and confusion-aware training to better distinguish highly co-occurring relations in sentences.

Contribution

The paper proposes a new approach combining Entity-Guided Attention and Confusion-Aware Training to improve relation decoupling in few-shot classification tasks.

Findings

CTEG achieves superior accuracy on FewRel dataset.

EGA effectively filters out confusing information.

CAT enhances the model's ability to distinguish similar relations.

Abstract

This paper aims to enhance the few-shot relation classification especially for sentences that jointly describe multiple relations. Due to the fact that some relations usually keep high co-occurrence in the same context, previous few-shot relation classifiers struggle to distinguish them with few annotated instances. To alleviate the above relation confusion problem, we propose CTEG, a model equipped with two mechanisms to learn to decouple these easily-confused relations. On the one hand, an Entity-Guided Attention (EGA) mechanism, which leverages the syntactic relations and relative positions between each word and the specified entity pair, is introduced to guide the attention to filter out information causing confusion. On the other hand, a Confusion-Aware Training (CAT) method is proposed to explicitly learn to distinguish relations by playing a pushing-away game between classifying a sentence into a true relation and its confusing relation. Extensive experiments are conducted on the FewRel dataset, and the results show that our proposed model achieves comparable and even much better results to strong baselines in terms of accuracy. Furthermore, the ablation test and case study verify the effectiveness of our proposed EGA and CAT, especially in addressing the relation confusion problem.