Interactively Exploring a Machine Translation Model

This paper describes a method of in-teractively visualizing and directing the process of translating a sentence. The method allows a user to explore a model of syntax-based statistical machine trans-lation (MT), to understand the model’s strengths and weaknesses, and to compare it to other MT systems. Using this visual-ization method, we can find and address conceptual and practical problems in an MT system. In our demonstration at ACL, new users of our tool will drive a syntax-based decoder for themselves.