Academic Division: Information Engineering
Research group: Machine Intelligence
Telephone: +44 1223 3 32754
The area of machine translation (MT) studies the automatic translation from one natural language to another. Count-based statistical models have been dominating open domain MT for the last decades. For the last few years, however, the field is experiencing a clear shift towards neural machine translation which carries out the translation by using a single neural network. Neural MT is in stark contrast to traditional statistical MT, and both paradigms have complementary strengths and weaknesses. Therefore, I try to bridge the gap between traditional and neural MT. I am not only interested in system-level combination schemes, but I think that by using neural models for word alignments which are essential to count-based models, or designing specialized neural network architectures, neural and traditional MT could benefit from each other on a more profound level. My goal is to apply lessons learnt in the last decades of MT research to the new paradigm of neural machine translation.
Department role and responsibilities