We describe Joshua, an open source toolkit for statistical machine translation. Joshua implements all of the algorithms required for synchronous context free grammars (SCFGs): chart-parsing, n-gram language model integration, beamand cube-pruning, and k-best extraction. The toolkit also implements suffix-array grammar extraction and minimum error rate training. It uses parallel and distributed computing techniques for scalability. We demonstrate that the toolkit achieves state of the art translation performance on the WMT09 French-English translation task. 1

Abstract � � ������� � � ������� � ������ � �� � ������������ � ������ � ����������� � � � ������ � � � ������ � �� ����In�� � many ��������� � cases in�� � SMT �� � �������� � we want ��������� � to allow �������� � specialized � � modules ������� � ���� � to propose �� � �� � translation �� � ��������� � fragments �������to ������������� � the decoder n���� � and allow ������� � them���� � to compete ����������� � with ���� � translations �� � ������������ � contained ���ink���� � the phrase ������� table. ���� � ������������ � Transliteration ������� � is one �� � module ���������� � that �������� � may produce ��������� � such �� � specialized ���������output. � � ��� � In � � �������� � this paper, �� as ���������� � an example, ������������� � we build a��� � specialized �� � ������ � Urdu � � ��� � transliteration ��� � � � ���� � ����� � module ����and � ������� � integrate ������ � its output ������� into � � ������ � an Urdu–English MT system. The module marks-up the test text using an XML format, and the decoder allows alternate translations (transliterations) to compete. 1.