Translating Foreign Languages
Computer scientists and linguists have created automated translation programs that can roughly translate back and forth in many of the world’s major languages. These programs are steadily improving, thanks to the work of researchers like associate professor of computer science Dan Gildea and his colleagues at the University.
Gildea works in the field known as machine translation (an aspect of machine learning), an area of natural language processing. Today’s systems, such as “Google Translate,” are based on simple word and phrase frequencies, and as a result often make wrong and misleading translations. For example, translating “Love your work and you’ll never be bored” into Japanese and back yields “Love your work, you are bored.” Gildea is using Big Data to help pioneer algorithms for high-quality translation that take into account the deep syntactic structure of language.