This ends in publishing of large scholarly material with no semantic meaning for machine understanding, as the legacy documents goes through information loss during substitution of fonts in migration strategy. In the early days, no one gave its attention towards the standard format of these Indian language fonts. Fonts were the key element for digital publishing. The Indian scholarly articles and books were digitally published in Indic scripts over the internet for open public access. With time, Indian scholarly and library community was also influenced by the evolution of computers at great extent. All the big industries and business houses started using computers instead of manpower for their day‐ to‐day work. This era has introduced the India to the modern computer systems. In the start of 1990's, India has seen a great boost in the information science world. In the proposed system, we have developed a web interface that facilitates the updation and query-based results retrieval of entries from lexical database. We have studied different approaches adopted for the construction of lexical databases of different languages in the world. Our work includes design and construction of such a database for Pakistani regional languages. English WordNet developed by Princeton University is a best example of lexical database. These are the main motivations behind this research.
The lexical databases for the developed languages are already built, but less attention is given to less resourced or under resourced languages like Punjabi, Saraiki etc. So there is a rich need to develop such resources. All these tasks also need large scale lexical databases.
Natural language processing or natural language engineering has many tasks such as word sense disambiguation, machine translation, part of speech tagging and such others. So for the cross lingual information processing there should be some centralized repository of words, usually known as a lexical database. Pakistan is a multilingual country where different languages are being spoken by its people.
0 kommentar(er)
