Syntactic, Semantic and Lexical Language Models for Machine Translation

Statistical machine translation systems have seen increasing success in recent years, due to improved statistical methods and larger quantities of training data. Common to all statistical approaches along this spectrum, however, is the research focus on syntax or phrase based translation models, while maintaining the use of simplest language models, n-grams, in decoding algorithms. This project builds composite complex language models to improve the performance of machine translation systems.

• Funding: Google
• PI/Contact: Prof. Shaojun Wang