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