Relation Classification via Recurrent Neural Network
This work addresses relation classification for natural language processing applications, offering an incremental improvement by using RNNs over CNNs for better handling of long-distance patterns.
The paper tackled relation classification by proposing a recurrent neural network (RNN) framework to address the limitation of CNN-based methods in learning long-distance dependencies, achieving better performance on two datasets, including a refined MIMLRE dataset.
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.