This paper extends the training and tuning regime for phrase-based statistical machine translation to obtain fluent translations into morphologically complex languages (we build ...
The LOGON MT demonstrator assembles independently valuable general-purpose NLP components into a machine translation pipeline that capitalizes on output quality. The demonstrator ...
State-of-the-art Machine Translation (MT) systems are still far from being perfect. An alternative is the so-called Interactive Machine Translation (IMT) framework. In this framew...
In this paper, we demonstrate that accurate machine translation is possible without the concept of “words,” treating MT as a problem of transformation between character string...
Graham Neubig, Taro Watanabe, Shinsuke Mori, Tatsu...
In modern machine translation practice, a statistical phrasal or hierarchical translation system usually relies on a huge set of translation rules extracted from bi-lingual traini...