Collocation and Term Extractor

CollTerm

CollTerm is a language independent tool for collocation and term extraction. It is an application that collects collocation and term candidates based on five different co occurrence measures for multiword units (i.e. collocations) or distributional differences from large representative corpus by application of the TF-IDF measurement on singleword units. The language dependent part consists of stop-word list and list of MWU MSD-patterns that can be coded with regular expressions as well. The application is describe in the paper presented at TKE2012 by Pinnis, M., Ljubešić, N., Ştefănescu, D., Skadiņa, I, Tadić, Gornostay, T. Term Extraction, Tagging, and Mapping Tools for Under-Resourced Languages. The first version of this application is available as an integral part of ACCURAT Toolkit that is available under Apache 2.0 license (http://www.accurat-project.eu/index.php?p=accurat-toolkit). In this version of the tool a calibration of MWU MSD-patterns has been provided for Croatian thus enhancing the usability of the tool. The plan is to provide calibration for other CESAR languages as well.