Completed Projects

Real-time font encoding converting tool that runs in your web browser. It facilitates the encoding conversion from proprietary fonts to Unicode and vice versa for both Sinhala and Tamil. This tool currently supports DL-Manel, FM Abhaya, Thibus, kaputa and Amalee Sinhala fonts and Bamini Tamil font.

Language Technology Research Laboratory – UCSC

Two online keyboards for Sinhala: virtual Sinhala keyboard and phonetic keyboard. Both keyboards help the users to type in Sinhala very easily.

Language Technology Research Laboratory – UCSC

Download

Tamil OCR is an Optical Character Recognition system for Tamil script. This enables conversion of images in Tamil text into machine-readable text. This OCR system supports for .jpg file type and output text will be in Tamil Unicode without formatting.

Visit

Si-Ta is a collaborative effort between the National Languages Processing Centre, the Department of Official Languages (DOL) and Ministry of National Co-existence, Dialogue & Official Languages. Si-Ta currently supports the translation of short official documents between Sinhala-to-Tamil and Tamil-to-Sinhala.

Visit

A new Sinhala POS tag set that overcomes the limitations of the previous Sinhala POS tag set. A corpus of 400,000 words have been manually annotated, which in turn was used to train different supervised classifiers.

Visit

A morphological synthesizer for Sinhala nouns, which works with a reasonable accuracy.

Visit