One of the supporting functions of SADiLaR is providing researchers with easily accessible technologies that can support their research efforts. Over the course of the project, SADiLaR will provide access to these technologies through relatively simple web interfaces that allow access to data and some of the technologies that are available from the SADiLaR repository. Currently there are only a limited number of technologies available, but this will be extended on a regular basis, to not only include those technologies that are available from SADiLaR, but also to those services provided by our partner nodes.
Currently, the following technologies are available:
A service that allows for online searches in the corpora available from SADiLaR, and includes the following functionality:
- Key word in context searches;
- Word and frequency list generation;
- Filtering of data based on metadata annotations;
- Part-of-speech and lemma-based searches.
A collection of 61 text technologies that are made available as web services and a simple user interface to automatically process textual input. The technologies are available for all indigenous South African languages, and include:
- Optical character recognition engines;
- Language identifier;
- Sentence boundary detection;
- Tokenisers;
- Part-of-speech taggers;
- Named-entity recognisers;
- Phrase chunkers.
The MTWS is a unified interface through which anyone can gain access to the MT systems developed in the Autshumato project. It can provide sentence, document and web page translation in any of the available language pairs. New MT systems can easily be added to the MTWS to be instantly available to anyone with an internet connection. Currently the MTWS supports the following language pairs:
- English to Afrikaans;
- English to isiZulu;
- English to Sesotho sa Leboa;
- English to Setswana;
- English to Xitsonga.
