 | Conversion of Punjabi text in Shahmukhi (Urdu) script to Gurmukhi script with the click of a mouse |
| |
| |
| Transliteration accuracy to be more than 97% at word level. |
| |
| |
| Support for popularly used Shahmukhi fonts, formats and encoding standards |
| |
| |
| Built-in filter for DOC, RTF and HTML file formats as well as Unicode and ASCII text files. |
| |
| |
| Gurmukhi Output to be made available in Unicode, as well as font encoded files, DOC, RTF and HTML File formats. |
| |
| |
As part of this process the following tools will also be developed:
|
| Development of Shahmukhi-Gurmukhi Dictionary |
| |
| |
| Development of rules for transliteration from Shahmukhi to Gurmukhi |
| |
| |
| Development of Shahmukhi Corpus (Huge collection of text) for statistical analysis (such as frequency analysis, bigram and trigram analysis) to resolve the ambiguity regarding correct Gurmukhi word to be replaced, wherever there are more than one choices for a Shahmukhi word |
| |
| |
| Development of module for context analysis of Shahmukhi text to fill up the diacritical marks of Shahmukhi text in Gurmukhi |
| |
| |
| Development of Shahmukhi Morphological analyzer. A Morphological analyser gives the morph analysis of a word i.e. for a given word it will return its root word along with other grammatical information depending upon its word class. |
| |
| |
