Learning approaches for natural language processing

Stefan Wermter, Ellen Riloff, Gabriele Scheler

Abstract: The purpose of this chapter is to provide an introduction to the field of connectionist, statistical and symbolic approaches to learning for natural language processing, based on the contributions in this book. The introduction has been split into three parts: (1) neural networks and connectionist approaches, (2) statistical approaches, and (3) symbolic machine learning approaches. We will give a brief overview of the main methods used in each field, summarize the work that is presented here, and provide some additional references. In the final section we will highlight important general issues and trends based on the workshop discussions and book contributions.