Benjamin Tsou has worked in natural language processing for over 20 years. He and his team at Chilin (HK) Ltd. have cultivated a large database of over 300,000 parallel Chinese and English patents from which over 30 million high-quality sentence pairs ideal for machine translation training have been extracted. From these they obtained over one million bilingual technical terms and produced an award-winning innovative post-editing platform PatentLex. Their efforts in language database cultivation also includes a 25-year long synchronous corpus of media material from six major Chinese communities, LIVAC. It has provided a useful means to monitor linguistic and social-cultural trends comparatively.
Upcoming Sessions for Benjamin Tsou
There are no upcoming sessions to display.