Eastern Promise: Scientists in Ireland and India pledge to erode English-Indian Language Barrier
Ireland’s Centre for Next Generation Localisation and India’s Language Technologies Research Centre to collaborate on development of ground-breaking English-Indian translation systems
20 May 2011, Dublin, Ireland – Researchers at two of the world’s major language technology research centres have committed their joint efforts to enhance the quality of translation from English to the major languages of India. Pioneers at Ireland’s Centre for Next Generation Localisation (CNGL) and the Language Technologies Research Centre (LTRC) at the International Institute of Information Technology Hyderabad (IIIT Hyderabad) will collaborate to build accurate translation systems from English to Indian languages. In addition to core funding from Science Foundation Ireland, the work will be supported by The Government of India through its India-Ireland Cooperative Science Programme and by CNGL academic partner Dublin City University through its DCU India Fund.
The outcomes of the two-year project are likely to have great social and commercial value. Accurate machine translation systems will reduce the cost and time associated with preparing (or ‘localising’) software and other digital content for international markets. The new systems will help Irish companies to communicate with India’s more than 1.2 billion consumers in their own language. They will also enable Indian companies to target not just Irish consumers in their native tongue, but the wider English-speaking world. With 72 per cent of consumers more likely to buy a product with information in their own language, there are substantial economic benefits associated with enabling companies to provide products and services to international customers in their native tongue.
The potential benefits of the research are not solely economic. Professor Andy Way, Principal Investigator at CNGL explains, “The social benefits of high-quality machine translation include wider access to digital content that was produced originally in another language. For example, speakers of Hindi with limited or no knowledge of English may be able to view accurate real-time translations of online content on topics that interest them – be it major sporting events, vital health information, or emergency response guidance.”
This new collaboration on English-Indian translation systems will continue the mutually-beneficial partnership on localisation R&D between Ireland and India – two significant players on the localisation world stage. The project will focus on syntax-driven approaches for statistical machine translation into Indian languages. As Way explains, “The Centre for Next Generation Localisation’s new collaboration with IIIT Hyderabad will help us to essentially “unlock” digital content, products and services in Indian languages – some of which are among the most widely spoken in the world. For the people of India, we aim to make English-language content more easily accessible in their own language, thereby opening up a world of digital content, products and services that was previously beyond their reach.”
CNGL has on-going collaborative research projects with a range of industry and academic partners in India. These include IIIT Hyderabad and the Centre for Development of Advanced Computing (CDAC) in Pune. CDAC Pune and CNGL have been collaborating on the creation of a community platform for The Rosetta Foundation for the past year. The Rosetta Foundation is an activity spun out of CNGL, which aims to relieve poverty, support healthcare, develop education and promote justice through access to information and knowledge across the languages of the world.
