| model,7-1-N03-2036,ak | In this paper , we describe a <term> phrase-based unigram model </term> for <term> statistical machine translation </term> that uses a much simpler set of <term> model parameters </term> than similar <term> phrase-based models </term> . | #3397 In this paper, we describe aphrase-based unigram model for statistical machine translation that uses a much simpler set of model parameters than similar phrase-based models. | |
| tech,11-1-N03-2036,ak | In this paper , we describe a <term> phrase-based unigram model </term> for <term> statistical machine translation </term> that uses a much simpler set of <term> model parameters </term> than similar <term> phrase-based models </term> . | #3401 In this paper, we describe a phrase-based unigram model forstatistical machine translation that uses a much simpler set of model parameters than similar phrase-based models. | |
| other,21-1-N03-2036,ak | In this paper , we describe a <term> phrase-based unigram model </term> for <term> statistical machine translation </term> that uses a much simpler set of <term> model parameters </term> than similar <term> phrase-based models </term> . | #3411 In this paper, we describe a phrase-based unigram model for statistical machine translation that uses a much simpler set ofmodel parameters than similar phrase-based models. | |
| model,25-1-N03-2036,ak | In this paper , we describe a <term> phrase-based unigram model </term> for <term> statistical machine translation </term> that uses a much simpler set of <term> model parameters </term> than similar <term> phrase-based models </term> . | #3415 In this paper, we describe a phrase-based unigram model for statistical machine translation that uses a much simpler set of model parameters than similarphrase-based models. | |
| other,1-2-N03-2036,ak | The <term> units of translation </term> are <term> blocks </term> - pairs of <term> phrases </term> . | #3419 Theunits of translation are blocks - pairs of phrases. | |
| other,5-2-N03-2036,ak | The <term> units of translation </term> are <term> blocks </term> - pairs of <term> phrases </term> . | #3423 The units of translation areblocks - pairs of phrases. | |
| other,9-2-N03-2036,ak | The <term> units of translation </term> are <term> blocks </term> - pairs of <term> phrases </term> . | #3427 The units of translation are blocks - pairs ofphrases. | |
| tech,1-3-N03-2036,ak | During <term> decoding </term> , we use a <term> block unigram model </term> and a <term> word-based trigram language model </term> . | #3430 Duringdecoding, we use a block unigram model and a word-based trigram language model. | |
| model,6-3-N03-2036,ak | During <term> decoding </term> , we use a <term> block unigram model </term> and a <term> word-based trigram language model </term> . | #3435 During decoding, we use ablock unigram model and a word-based trigram language model. | |
| model,11-3-N03-2036,ak | During <term> decoding </term> , we use a <term> block unigram model </term> and a <term> word-based trigram language model </term> . | #3440 During decoding, we use a block unigram model and aword-based trigram language model. | |
| tech,1-4-N03-2036,ak | During <term> training </term> , the <term> blocks </term> are learned from <term> source interval projections </term> using an underlying <term> word alignment </term> . | #3446 Duringtraining, the blocks are learned from source interval projections using an underlying word alignment. | |
| other,4-4-N03-2036,ak | During <term> training </term> , the <term> blocks </term> are learned from <term> source interval projections </term> using an underlying <term> word alignment </term> . | #3449 During training, theblocks are learned from source interval projections using an underlying word alignment. | |
| other,8-4-N03-2036,ak | During <term> training </term> , the <term> blocks </term> are learned from <term> source interval projections </term> using an underlying <term> word alignment </term> . | #3453 During training, the blocks are learned fromsource interval projections using an underlying word alignment. | |
| model,14-4-N03-2036,ak | During <term> training </term> , the <term> blocks </term> are learned from <term> source interval projections </term> using an underlying <term> word alignment </term> . | #3459 During training, the blocks are learned from source interval projections using an underlyingword alignment. | |
| model,5-5-N03-2036,ak | We show experimental results on <term> block selection criteria </term> based on <term> unigram counts </term> and <term> phrase length </term> . | #3467 We show experimental results onblock selection criteria based on unigram counts and phrase length. | |
| other,10-5-N03-2036,ak | We show experimental results on <term> block selection criteria </term> based on <term> unigram counts </term> and <term> phrase length </term> . | #3472 We show experimental results on block selection criteria based onunigram counts and phrase length. | |
| other,13-5-N03-2036,ak | We show experimental results on <term> block selection criteria </term> based on <term> unigram counts </term> and <term> phrase length </term> . | #3475 We show experimental results on block selection criteria based on unigram counts andphrase length. |
