ONTS: "Optima" News Translation System
This addresses the problem of translating large volumes of live news articles efficiently for users needing real-time access to multilingual news, though it appears incremental with optimizations of existing methods.
The researchers developed a real-time machine translation system optimized for news articles that automatically categorizes content, improves named entity translation, uses specialized title translation, and prioritizes speed to handle high volumes. The system translates from 11 languages into English with domain-specific optimizations.
We propose a real-time machine translation system that allows users to select a news category and to translate the related live news articles from Arabic, Czech, Danish, Farsi, French, German, Italian, Polish, Portuguese, Spanish and Turkish into English. The Moses-based system was optimised for the news domain and differs from other available systems in four ways: (1) News items are automatically categorised on the source side, before translation; (2) Named entity translation is optimised by recognising and extracting them on the source side and by re-inserting their translation in the target language, making use of a separate entity repository; (3) News titles are translated with a separate translation system which is optimised for the specific style of news titles; (4) The system was optimised for speed in order to cope with the large volume of daily news articles.