Combining Recurrent and Convolutional Neural Networks for Relation Classification
This work addresses relation classification in natural language processing, an incremental improvement over existing methods.
The paper tackled relation classification by investigating convolutional and recurrent neural networks, proposing new context representations and ranking loss, and achieved state-of-the-art results on the SemEval 2010 task.
This paper investigates two different neural architectures for the task of relation classification: convolutional neural networks and recurrent neural networks. For both models, we demonstrate the effect of different architectural choices. We present a new context representation for convolutional neural networks for relation classification (extended middle context). Furthermore, we propose connectionist bi-directional recurrent neural networks and introduce ranking loss for their optimization. Finally, we show that combining convolutional and recurrent neural networks using a simple voting scheme is accurate enough to improve results. Our neural models achieve state-of-the-art results on the SemEval 2010 relation classification task.