Automatic detection of general relations between short texts is a complex task that cannot be carried out only relying on language models and bag-of-words. Therefore, learning methods to exploit syntax and semantics are required. In this paper, we present a new kernel for the representation of shallow semantic information along with a comprehensive study on kernel methods for the exploitation of syntactic/semantic structures for short text pair categorization. Our experiments with Support Vector Machines on question/answer classification show that our kernels can be used to greatly improve system accuracy. .
