This article defines a Framework for Machine Translation Evaluation (FEMTI) which relates the quality model used to evaluate a machine translation system to the purpose and context...
Eduard H. Hovy, Margaret King, Andrei Popescu-Beli...
This paper extends the training and tuning regime for phrase-based statistical machine translation to obtain fluent translations into morphologically complex languages (we build ...
In current phrase-based Statistical Machine Translation systems, more training data is generally better than less. However, a larger data set eventually introduces a larger model ...
Tree Adjoining Grammars have well-known advantages, but are typically considered too difficult for practical systems. We demonstrate that, when done right, adjoining improves tran...
Even though multilingual communities that use machine translation to overcome language barriers are increasing, we still lack a complete understanding of how machine translation a...