Multi-Level Matching and Aggregation Network for Few-Shot Relation Classification

TL;DR

This paper introduces MLMAN, a novel multi-level matching and aggregation network for few-shot relation classification that outperforms previous methods by encoding query and support sets interactively at multiple levels.

Contribution

The paper proposes a multi-level matching and aggregation approach that considers local and instance-level interactions, achieving state-of-the-art results on FewRel.

Findings

Achieves new state-of-the-art performance on FewRel dataset.

Effectively models query-support interactions at multiple levels.

Improves relation classification accuracy in few-shot settings.

Abstract

This paper presents a multi-level matching and aggregation network (MLMAN) for few-shot relation classification. Previous studies on this topic adopt prototypical networks, which calculate the embedding vector of a query instance and the prototype vector of each support set independently. In contrast, our proposed MLMAN model encodes the query instance and each support set in an interactive way by considering their matching information at both local and instance levels. The final class prototype for each support set is obtained by attentive aggregation over the representations of its support instances, where the weights are calculated using the query instance. Experimental results demonstrate the effectiveness of our proposed methods, which achieve a new state-of-the-art performance on the FewRel dataset.