Improved Relation Classification by Deep Recurrent Neural Networks with Data Augmentation
This work addresses relation classification for natural language processing, but it is incremental as it builds on existing neural methods with architectural and data enhancements.
The paper tackled the problem of shallow neural networks in relation classification by proposing deep recurrent neural networks (DRNNs) with data augmentation, achieving an F1-score of 86.1% on SemEval-2010 Task 8 and outperforming previous state-of-the-art results.
Nowadays, neural networks play an important role in the task of relation classification. By designing different neural architectures, researchers have improved the performance to a large extent in comparison with traditional methods. However, existing neural networks for relation classification are usually of shallow architectures (e.g., one-layer convolutional neural networks or recurrent networks). They may fail to explore the potential representation space in different abstraction levels. In this paper, we propose deep recurrent neural networks (DRNNs) for relation classification to tackle this challenge. Further, we propose a data augmentation method by leveraging the directionality of relations. We evaluated our DRNNs on the SemEval-2010 Task~8, and achieve an F1-score of 86.1%, outperforming previous state-of-the-art recorded results.