Multi-Scale Feature and Metric Learning for Relation Extraction

TL;DR

This paper introduces a multi-scale feature and metric learning framework that enhances relation extraction by aggregating lexical and syntactic features at multiple scales, leading to significant performance improvements.

Contribution

It proposes novel multi-scale convolutional and graph convolutional networks combined with metric learning for more effective relation extraction.

Findings

Outperforms state-of-the-art methods on three datasets

Effectively aggregates non-successive lexical features

Increases receptive field for syntactic features

Abstract

Existing methods in relation extraction have leveraged the lexical features in the word sequence and the syntactic features in the parse tree. Though effective, the lexical features extracted from the successive word sequence may introduce some noise that has little or no meaningful content. Meanwhile, the syntactic features are usually encoded via graph convolutional networks which have restricted receptive field. To address the above limitations, we propose a multi-scale feature and metric learning framework for relation extraction. Specifically, we first develop a multi-scale convolutional neural network to aggregate the non-successive mainstays in the lexical sequence. We also design a multi-scale graph convolutional network which can increase the receptive field towards specific syntactic roles. Moreover, we present a multi-scale metric learning paradigm to exploit both the feature-level relation between lexical and syntactic features and the sample-level relation between instances with the same or different classes. We conduct extensive experiments on three real world datasets for various types of relation extraction tasks. The results demonstrate that our model significantly outperforms the state-of-the-art approaches.