Abstract | ||
---|---|---|
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 order-based 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. |
Year | Venue | Keywords |
---|---|---|
2008 | EMNLP | coarse-to-fine syntactic machine translation,machine translation decoding,bigram-to-trigram decoder,trigram language model,multiple language pair,entire decoding cascade,target language,tree transducer-based translation model,language model complexity,language projection,previous order-based bigram-to-trigram approach,n-gram language models result,language model,machine translation |
Field | DocType | Volume |
Rule-based machine translation,Example-based machine translation,Cache language model,Trigram,Computer science,Machine translation,Speech recognition,Transfer-based machine translation,Natural language processing,Artificial intelligence,Low-level programming language,Language model | Conference | D08-1 |
Citations | PageRank | References |
22 | 1.00 | 21 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Slav Petrov | 1 | 2405 | 107.56 |
Aria Haghighi | 2 | 1250 | 62.54 |
Dan Klein | 3 | 8083 | 495.21 |