Statistical Phrase-Based Post-Editing

This article describes a machine translation system based on an automatic post-editing strategy: initially translate the input text into the target-language using a rule-based MT system, then automatically post-edit the output using a statistical phrase-based system. An implementation of this approach based on the SYSTRAN and PORTAGE MT systems was used in the shared task of the Second Workshop on Statistical Machine Translation. Experimental results on the test data of the previous campaign are presented.

• Type: Conference
• Year: 2007
• Where: NAACL
• Authors: Michel Simard, Cyril Goutte, Pierre Isabelle
• Keywords: Computational Linguistics, Machine Translation, MT Systems, NAACL 2007, Statistical Phrase-based System