| Year |
Beginning of Activity |
Output |
|
| First Year Schedule |
|
| Month 1 |
System analysis and design. Study of standards and formats used for storing Shahmukhi and Gurmukhi scripts. |
Refresher workshop for Urdu and Punjabi languages.System Analysis and Design |
| Month 2 |
Selection of 25,000 most frequently used Shahmukhi-Gurmukhi terms.Design of Lexical entry interface and lexical entry of these terms. |
Data entry of 5,000 Shahmukhi-Gurmukhi terms |
| Month 3 |
Development of mapping tables and transliteration rules for transliteration of Shahmukhi to Gurmukhi. |
Data entry of 10,000 Shahmukhi-Gurmukhi terms.Mapping tables and transliteration rules completed. |
| Month 4 |
Implementation of mapping tables and transliteration rules |
Data entry of 15,000 Shahmukhi-Gurmukhi terms.A rule-based primitive version of the Transliteration software ready. |
| Month 5 |
Selection of representative corpus of Shahmukhi text of at least 3 million words. |
Data entry of 20,000 Shahmukhi-Gurmukhi terms. |
| Month 6 |
Design of database for storing the corpus and other tables to be used in the software. |
Data entry of 25,000 Shahmukhi-Gurmukhi terms. Development of a half million word corpus |
| Month 7 |
Integration of Shahmukhi-Gurmukhi dictionary with the rule based Transliteration software. |
Development of one million word corpus.Rule and dictionary based version of the Shahmukhi-Gurmukhi Transliteration software. |
| Month 8 |
Design of modules for context analysis of Shahmukhi text including statistical and natural language processing. |
Development of one and half million word corpus.Development of module for statistical of Shahmukhi text including unigram, bigram and trigram analysis. |
| Month 9 |
Development of morphological analyzer for the Shahmukhi text. |
Development of two million word corpus |
| Month 10 |
Continue with corpus development. |
Development of two and half million word corpus |
| Month 11 |
Continue with corpus development. |
Development of three million word corpus |
| Month 12 |
Integration of the corpus with the other modules of the transliteration software |
Development of beta version of the transliteration software. The software will be using a combination of translitertion rules and mapping table, Shahmukhi-Gurmukhi dictionary and statistical and context analysis of the Shahmukhi corpus. |
|
| Second Year Schedule |
|
| Month 13 |
Testing of the beta version on carefully selected text. |
Validation and removing of bugs in the beta version. |
| Month 14 |
Continue testing on more text. |
Validation of software. |
| Month 15 |
Continue testing on more text. |
Validation of software. |
| Month 16 |
Design the online version of the software to be deployed on the internet. |
Implementation of some of modules of online version of transliteration software |
| Month 17 |
Continue with development of online version |
Implementation of some of modules of online version of transliteration software |
| Month 18 |
Continue with development of online version |
Development of online version of transliteration software |
| Month 19 |
Testing of the online version on different operating systems and browsers |
Validation of online version |
| Month 20 |
Continue testing of the online version on different operating systems and browsers |
Validation of online version |
| Month 21 |
Installation, User testing and field testing of final version |
Validation of both the offline and online versions of the software |
| Month 22 |
Getting feedback from users |
Validation of both the offline and online versions of the software based on the user feedback. |
| Month 23 |
Continue with validation of the software |
Final version of the software ready. |
| Month 24 |
Documentation and packaging of the system |
Documentation and software development complete. |
|
| |
|
