Tools and resources:

last 5 tools

BootCaT CorpCleaner v1.0
tool for cleaning BootCaT corpora, ie. for the removal of redundant sequences of characters from specialised corpora obtained by the BootCaT tool; Python

CroSS 2.0: Croatian Speech Synthesizer
application for the formant and diphone computational synthesis of speech in Croatian; C++

Trans2Me: integrated multilingual dictionary of specific terminology
tool for searching and obtaining legal terminology of the European Union and specific administrative-bureaucratic terminology, for processing particular records, identification of multilingual translation pairs, entry and storage of new language knowledge (currently 41.000 tokens, incrementally rising); MS Access, SQL

ICReal: Crawling Digital Archive of Theses in Information and Communication Sciences in Real-Time
web application for advanced browsing of a digital archive containing works from the fields of information and communication sciences based on metadata (Dublin Core structure) in real time; PHP, MySQL, XML, Ajax, JavaScript, HTML, CSS

CroSS 1.0: Croatian Speech Synthesizer
application for the formant computational synthesis of speech in Croatian; C++

resources

statistical models for modelling and building statistical machine translation systems

dictionaries

tokenised corpora

annotated corpora

monolingual corpora

comparable corpora

aligned parallel corpora