This paper describes the Tenjinno Machine Translation Competition held as part of the International Colloquium on Grammatical Inference 2006. The competition aimed to promote the development of new and better practical grammatical inference algorithms used in machine translation. Tenjinno focuses on formal models used in machine translation. We discuss design issues and decisions made when creating the competition. For the purpose of setting the competition tasks, a measure of the complexity of learning a transducer was developed. This measure has enabled us to compare the competition tasks to other published results, and it can be seen that the problems solved in the competition were of a greater complexity and were solved with lower word error rates than other published results. In addition the complexity measures and benchmark problems can be used to track the progress of the state-of-the-art into the future.
展开▼
