An extensive empirical study of collocation extraction methods
Pavel Pecina · 2005
This paper presents a status quo of an ongoing research study of collocations -- an essential linguistic phenomenon having a wide spectrum of applications in the field of natural language processing. The core of the work is an empirical evaluation of a comprehensive list of automatic collocation extraction methods using precision-recall measures and a proposal of a new approach integrating multiple basic methods and statistical classification. We demonstrate that combining multiple independent techniques leads to a significant performance improvement in comparison with individual basic methods.