Extending MARIE: an N-gram-based SMT decoder

In this paper we present several extensions of MARIE1 , a freely available N-gram-based statistical machine translation (SMT) decoder. The extensions mainly consist of the ability to accept and generate word graphs and the introduction of two new N-gram models in the loglinear combination of feature functions the decoder implements. Additionally, the decoder is enhanced with a caching strategy that reduces the number of N-gram calls improving the overall search efficiency. Experiments are carried out over the Eurpoean Parliament Spanish-English translation task.

• Type: Conference
• Year: 2007
• Where: ACL
• Authors: Josep Maria Crego, José B. Mariño
• Keywords: ACL 2007, Computational Linguistics, Decoder Implements, Parliament Spanish-English Translation, Statistical Machine Translation