TermExtractor: a Web Application to Learn the Common Terminology of Interest Groups and Research Communities

Abstract

We implemented a high-performing technique to automatically extract from the available documents in a given domain the shared terminology of a web community. This technique has been successfully experimented and submitted for large-scale evaluation in the domain of enterprise interoperability, by the member of the INTEROP network of excellence. In order to make the technique available to any web community in any domain, we developed a web application that allows users to i) acquire (incrementally or in a single step) a terminology in any domain, by submitting documents of variable length and format, and ii) validate on-line the obtained results. The system also supports collaborative evaluation by a group of experts. The web application has been widely tested in several domains by many international institutions that volunteered for this task.