Software

New technologies provide exciting new opportunities for rapid and large volume of translation at relatively low cost. A number of different organisations are involved in the development of software for Machine Aided Translation.

NTM will not replicate these efforts by C-DAC, TDIL, the IITs, etc., which are already being extensively funded by the government. However, it could facilitate technological progress in Machine Translation by assisting in the training and development of human resources for some activities and assisting in others through collaboration and providing synergy.

NTM is also preparing In-Lan, an English Kannada Machine Translation package (rule based), of which the main aim is to automate the translation of given English sentences into Kannada.
  » Creation of the necessary infrastructure, especially of digital tools like online thesauri, bilingual dictionaries, software for translation memory, etc that have immediate application for more efficient and effective translation.
  » Lexical resources like e-dictionaries, WordNets, language analysis and synthesis tools, concordancers, frequency analysers etc. are the essential components of a Machine Translation system. These cannot be created and maintained by a single institute, but need multi-institute collaboration over a long time. NTM could provide a platform for team work, with continued interaction through meetings and online discussions.
  » Texts shortlisted by NTM and their translations should be made available in clean digital form as far as possible. NTM should ensure that this wealth of digital material is maintained in a standard from with standardised XML tags and DTDs.
  » The international trend these days is to develop good quality parallel corpora with annotations and alignments. Such annotated corpora are treated with machine learning techniques to obtain Machine Translation systems. The sheer volume of this data and the magnitude of the effort require substantial initial investments which are not ideally made by individual organisations; however, NTM could facilitate such efforts and provide some support.