Semantic tree kernels for statistical natural language learning

A central topic in Natural Language Processing (NLP) is the design of effective linguistic processors suitable for the target applications. Within this scenario, Convolution Kernels provide a powerful method to directly apply Machine Learning algorithms to complex structures representing linguistic information. The main topic of this work is the definition of the semantically Smoothed Partial Tree Kernel (SPTK), a generalized formulation of one of the most performant Convolution Kernels, i.e. the Tree Kernel (TK), by extending the similarity between tree structures with node similarities. The main characteristic of SPTK is its ability to measure the similarity between syntactic tree structures, which are partially similar and whose nodes can differ but are nevertheless semantically related. One of the most important outcomes is that SPTK allows for embedding external lexical information in the kernel function only through a similarity function among lexical nodes. The SPTK has been evaluated in three complex automatic Semantic Processing tasks: Question Classification in Question Answering, Verb Classification and Semantic Role Labeling. Although these tasks address different problems, state-of-the-art results have been achieved in every evaluation.