Coarse-to-Fine Syntactic Machine Translation using Language Projections

The intersection of tree transducer-based translation models with n-gram language models results in huge dynamic programs for machine translation decoding. We propose a multipass, coarse-to-fine approach in which the language model complexity is incrementally introduced. In contrast to previous orderbased bigram-to-trigram approaches, we focus on encoding-based methods, which use a clustered encoding of the target language. Across various encoding schemes, and for multiple language pairs, we show speed-ups of up to 50 times over single-pass decoding while improving BLEU score. Moreover, our entire decoding cascade for trigram language models is faster than the corresponding bigram pass alone of a bigram-to-trigram decoder.

• Type: Conference
• Year: 2008
• Where: EMNLP
• Authors: Slav Petrov, Aria Haghighi, Dan Klein
• Keywords: EMNLP 2008, Language Model Complexity, Language Models, N-gram Language Models, Natural Language Processing