Relation Classification via Recurrent Neural Network

TL;DR

This paper proposes an RNN-based framework for sentence-level relation classification, demonstrating its superiority over CNN models especially in capturing long-distance dependencies, with improved performance on multiple datasets.

Contribution

It introduces an RNN-based approach for relation classification and compares it with CNN models, highlighting its effectiveness in learning long-distance relations.

Findings

RNN-based model outperforms CNN on relation classification tasks

The model effectively captures long-distance dependency patterns

Experiments on two datasets show improved accuracy with RNNs

Abstract

Deep learning has gained much success in sentence-level relation classification. For example, convolutional neural networks (CNN) have delivered competitive performance without much effort on feature engineering as the conventional pattern-based methods. Thus a lot of works have been produced based on CNN structures. However, a key issue that has not been well addressed by the CNN-based method is the lack of capability to learn temporal features, especially long-distance dependency between nominal pairs. In this paper, we propose a simple framework based on recurrent neural networks (RNN) and compare it with CNN-based model. To show the limitation of popular used SemEval-2010 Task 8 dataset, we introduce another dataset refined from MIMLRE(Angeli et al., 2014). Experiments on two different datasets strongly indicates that the RNN-based model can deliver better performance on relation classification, and it is particularly capable of learning long-distance relation patterns. This makes it suitable for real-world applications where complicated expressions are often involved.