Judith L. Klavans is Director of the Center for Research on Information Access, Columbia University, which is responsible for linking theoretical computer science research with operational applications such as digital libraries and digital government. She is a principal investigator in several large projects, including the NSF-funded PERSIVAL medical digital library, the NSF and BLS supported Digital Government Research Center joint with University of Southern California-ISI, the DARPA-funded TIDES multilingual summarization project, and, most recently, the Mellon-supported CLiMB (Computational Linguistics for Metadata Building) project which links text and image collections.
Klavans focuses her research on computational linguistics and natural language processing (NLP). She is currently working on ways to analyze both monolingual and multilingual texts and to link meaningful segments via semantic nets and syntactic structure. She has worked on linguistic and statistical methods for extracting and linking information from large online texts. Klavans has developed a novel method of text mining to use automatic methods for the extraction of glossaries from text. She has also developed a web-crawler for the identification of glossaries from large government websites.
K-Collector