Selective kernel networks for weakly supervised relation extraction

Abstract

Abstract The purpose of relation extraction is to identify the semantic relations between entities in sentences that contain two entities. Recently, many variants of the convolution neural network (CNN) have been introduced to relation extraction for the extracting of features—the quality of the neural network model directly affects the final quality of relation extraction. However, the traditional convolution network uses a fixed convolution kernel, so it is difficult to choose the size of the convolution kernel dynamically, which results in networks with weak representation ability. To address this, a novel CNN is designed with selective kernel networks and multigranularity. In the process of feature extraction, the model can adaptively select the size of the convolution kernel, that is, give more weight to the appropriate convolution kernel. It is then combined with multigranularity convolution to obtain more abundant semantic information. Finally, a new pooling method is designed to obtain more comprehensive information and improve model performance. Experimental results indicate that this method is effective without excessively deep network layers, and it also outperforms several competitive baseline methods.

Keywords

• feature extraction
• operating system kernels
• supervised learning
• convolutional neural nets
• deep learning (artificial intelligence)