Machine Translation: An Introduction

This is the first blog in the series Machine Translation: An Overview by Dr. S. K. Srivastava.

India is a country of diversity that can be observed in every space – cultures, religions, food types, and languages, to name a few. Though diversity is the strength of this country, sometimes it becomes a hurdle. For instance, communication among people speaking different languages becomes an obstacle in social interaction as well as businesses and this brings us to the issue of language translation.  With 22 constitutionally recognized languages written in 12 scripts, the translation among Indian languages poses a more complex problem than in the case of the European Union with 24 major languages. As translation by humans is expensive and time-consuming, it is necessary to explore the use of technology to solve this problem. 

In the present era of globalization, translation does not only increase social interaction among the people speaking different languages but also plays a crucial role in business, education, governance, entertainment, etc. In the area of education, it has been observed that one major barrier in imparting quality education in Indian institutions is the non-availability of content in Indian languages. Though it is true in any area, more so in technical courses. We have several thousand hours of video lectures in English on most of the engineering courses under NPTEL but, there is hardly any content in Indian languages. Learning is always more natural in one’s native tongue. The government has announced to start the technical education programmes in local languages in some of the institutions. To make it successful, we need more efficient Machine-Aided Translation (MAT) systems or Fully Automatic Machine Translations (FAMT) systems also called Machine Translation (MT) systems to translate textbooks and video lectures into Indian languages.

The benefits of the IT revolution, especially, the internet can reach every citizen of India only when the content and services on Internet are made available in local languages. At present, it is largely limited to about 10% of English-speaking population. The remaining population depends on English-speaking people to get services and access to information. Translation of the information on the internet by humans will take several years. To bring the benefits of the IT revolution to the remaining 90% population in a limited time frame, it is necessary to use technology in translation.

Other blogs in this series:
Summary and Abstract
1.    Machine Translation: The International scenario
2.    Machine Translation: The National scenario
3.    The National Language Translation Mission

Acknowledgement

While preparing the article, several experts were consulted for their views and suggestion. Their contributions are gratefully acknowledged. In particular, I would like to thank Dr. P. K. Saxena and Prof. G. N. Jha for their suggestions. 

Disclaimer

The views presented in the article are those of the author and not the Office of Principal Scientific Adviser to the Government of India. Any comments/suggestions may be sent to the author at sks@meity.gov.in.