Mumbai: AICTE, the apex body for technical education, has opened doors for engineering education in eight Indian languages. Indian Institute of Technology has launched an AI-powered open source system that translates scientific and technical material from English to Hindi and other Indian languages.
To promote the study of engineering in regional languages, the team aims to translate 500 engineering texts into Hindi within a year and 15 Indian languages in three years. Using artificial intelligence, the system is expected to complete the task at one-sixth the speed at which translators would work manually.
Project Udaan, as this initiative is known, was launched seven years ago by Prof. was started as Ganesh RamakrishnanProfessor, Head of the Institute, Department of Computer Science and Engineering, IIT BombayAnd his team analyzed the wide gap in the availability of technical knowledge in Hindi and other Indian languages.
Commenting on the deployment of machine based translation for the project, Krishnaswamy VijayRaghavanThe Principal Scientific Adviser to the Government of India said: “Because of technology, because we can create glossaries in every field, because we can scan and digitize and translate, for most types of documents you can get a high degree of accuracy from a machine. based translation.”
However, he pointed out that “there will still be a great need for human intervention that will uncover the nuances that are needed for translation.”
He said that this effort speaks to the deep understanding of the society which is necessary to achieve excellence. “To excel in a field, you have to take root in your culture, your society and harness the power of your understanding that comes from your language. If you look at China, Japan, Sweden or Germany, education is mainly in their native language, but bilingual or trilingual abilities are common.
Professor Ramakrishnan said, “Our approach to machine translation has been that it will be aided by human effort. We started creating dictionaries for various technical domains. We have developed strong bilingual OCR Technology and many post-editing tools by which we now have access to digital bilingual dictionaries in machine readable format. Therefore, we are able to use suitable scientific and technical words available in Hindi instead of transliteration of English words.”
By deploying an AI-based translation engine, a technical book can be translated in less than one-sixth the time for a team of domain and language experts working manually. “Over time, we expect to achieve a much shorter turnaround time,” Ramakrishnan said.
To promote the study of engineering in regional languages, the team aims to translate 500 engineering texts into Hindi within a year and 15 Indian languages in three years. Using artificial intelligence, the system is expected to complete the task at one-sixth the speed at which translators would work manually.
Project Udaan, as this initiative is known, was launched seven years ago by Prof. was started as Ganesh RamakrishnanProfessor, Head of the Institute, Department of Computer Science and Engineering, IIT BombayAnd his team analyzed the wide gap in the availability of technical knowledge in Hindi and other Indian languages.
Commenting on the deployment of machine based translation for the project, Krishnaswamy VijayRaghavanThe Principal Scientific Adviser to the Government of India said: “Because of technology, because we can create glossaries in every field, because we can scan and digitize and translate, for most types of documents you can get a high degree of accuracy from a machine. based translation.”
However, he pointed out that “there will still be a great need for human intervention that will uncover the nuances that are needed for translation.”
He said that this effort speaks to the deep understanding of the society which is necessary to achieve excellence. “To excel in a field, you have to take root in your culture, your society and harness the power of your understanding that comes from your language. If you look at China, Japan, Sweden or Germany, education is mainly in their native language, but bilingual or trilingual abilities are common.
Professor Ramakrishnan said, “Our approach to machine translation has been that it will be aided by human effort. We started creating dictionaries for various technical domains. We have developed strong bilingual OCR Technology and many post-editing tools by which we now have access to digital bilingual dictionaries in machine readable format. Therefore, we are able to use suitable scientific and technical words available in Hindi instead of transliteration of English words.”
By deploying an AI-based translation engine, a technical book can be translated in less than one-sixth the time for a team of domain and language experts working manually. “Over time, we expect to achieve a much shorter turnaround time,” Ramakrishnan said.
.