In the last ten years natural language processing (NLP) has become an essential part of many information retrieval systems, mainly in the guise of question answering, summarization, machine translation and preprocessing such as decompounding. However, most of these methods are shallow. More complex natural language processing is not yet sufficiently reliable to be used in IR. I will discuss how new visualization technology and rich interactive environments offer new opportunities for complex NLP in IR.
Short Bio: Hinrich Schütze is best known for co-authoring the standard reference book on statistical natural language processing (http://nlp.stanford.edu/fsnlp/) (Google Scholar lists more than 4,700 citations of this book). His new book "Introduction to Information Retrieval" (http://nlp.stanford.edu/IR-book/information-retrieval-book.html) (co-authored with Chris Manning and Prabhakar Raghavan) was published in 2008 and has already been adopted by many IR courses throughout the world. Dr. Schütze obtained his PhD from Stanford University and has worked for a number of Silican Valley companies, including two large search engines and several text mining startups. He is currently Chair of Theoretical Computational Linguistics at the University of Stuttgart (www.ims.uni-stuttgart.de/~schuetze/).