Challenges and Opportunities of Multilingual Information Access

Abstract

The amount of digitally available information that is authored in languages other than English has been rapidly increasing over the last decade. This results in a distribution of information not only across different sources but also different languages. While various areas within natural language processing, such as machine translation, information extraction, and cross-language information retrieval, have made substantial advances over the last few years, they have done so mostly by addressing challenges that lie within the confines of their respective sub-area. Multilingual information access on the other hand spans the entire spectrum of these areas, requiring approaches that combine insights and methods that cross the boundaries of these individual research areas. In this talk, I will give an overview of a number of scenarios where cross-language technologies from different areas within natural language processing have benefited from each other in the past, but also discuss some of the challenges and opportunities that lie ahead of us.