An OCR system is an application that enables one to convert scanned paper documents into editable and searchable texts. The engine analyses the structure ...

A graphical user interface and command line tool to automatically classify a document, paragraph, sentence or phrase as one of the eleven official South ...

Aligned English-Xitsonga parallel corpus. The data is given as two seperate UTF-8 text files; with each segment on a newline.

Aligned English-Xitsonga parallel corpus. The data is given as two seperate UTF-8 text files; with each segment on a newline.

Word and phrase lists aligned from English to the other official South African languages.

Anonymises text by classifying and replacing sensitive information such as person names, business names, place names, monetary values, phone numbers, ...

Terminology Management System. Web application used by Terminologists and Administrators to capture, edit and export terminology.

Utility application for extracting text out of a PDF document. The pages can also be extracted as images.

Utility to merge multiple translation memories over a network using Subversion

Corpus query and manipulation tool for performing tokenisation and sentencisation; extracting frequency list and word list; searching; and extracting ...