Technology giant Microsoft is expected to sign a memorandum of understanding with the Ministry of Education as well as the Ministry of Culture and Fine Arts to help build a free online Khmer-language database for users to translate documents between Khmer and other languages, a Microsoft representative said Tuesday.
Government officials said the approvals for the project would come in the next two weeks.
The initiative will recruit local college students to translate English words and sentences to Khmer and input them into an online system known as the Microsoft Translator Hub. The hub will then compile a database of the translations that, once complete, will be made available for anyone to use for automatic translation.
But before the project can start, the company needs help from Cambodia’s ministries to oversee the translations and make sure they are accurate.
“We need them to do quality control and monitor the project,” said Chhourn Piseth, a technology specialist with Microsoft’s Development Program. “We’ve discussed this with the Ministry of Culture and Fine Arts and the Ministry of Education on how to make this plan a success.”
Mr. Piseth said the project is split into three phases, with the first phase expected to begin either next month or in early 2014, and for all phases to be nearly done within three years.
“We plan to finish the first stage within one year. During this time, we will input the most important words and basic sentences,” he said. “To maintain quality, there is no set time for the stages. But we want to be 90 percent complete in two to three years.”
Minister of Education Hang Chuon Naron said his ministry supports the project and would create a “pilot project” to help get it started.
“We’re interested and support this program, but we’ll continue to discuss it with Microsoft. Now, we are reviewing the memorandum of understanding,” he said. “I expect we will sign it within the next one or two weeks.”
© 2013, The Cambodia Daily. All rights reserved No part of this article may be reproduced in print, electronically, broadcast, rewritten or redistributed without written permission.