Simplicity is Better: Revisiting Single Kernel PPI Extraction

It has been known that a combination of multiple kernels and addition of various resources are the best options for improving effectiveness of kernel-based PPI extraction methods. These supplements, however, involve extensive kernel adaptation and feature selection processes, which attenuate the original benefits of the kernel methods. This paper shows that we are able to achieve the best performance among the stateof-the-art methods by using only a single kernel, convolution parse tree kernel. In-depth analyses of the kernel reveal that the keys to the improvement are the tree pruning method and consideration of tree kernel decay factors. It is noteworthy that we obtained the performance without having to use any additional features, kernels or corpora.