Friday, October 03, 2008
2:00 PM
CSB 632
Sam Zhao
University of Rochester
Finding massive and accurate translation pairs from the web
Statistical machine translation is a supervised learning problem, requiring a huge amount of training data to make the system produce good
quality translations. Given that high quality bilingual text is
expensive to get, we propose a method to mine massive and accurate
translation pairs from the web. Adding these translation pairs to a translation
system shows significant improvement in terms of translation quality.
We further propose a novel evaluation method using Wikipedia.