Concordance

Query N03-2036 17 >
Multilevel Sort 17 (792.6 per million)

model,11-3-N03-2036,bq	<term> block unigram model </term> and a <term>	word-based trigram language model	</term> . During <term> training </term> , the	#3439 During decoding, we use a block unigram model and aword-based trigram language model.
model,14-4-N03-2036,bq	projections </term> using an underlying <term>	word alignment	</term> . We show experimental results on	#3458 During training, the blocks are learned from source interval projections using an underlyingword alignment.
model,25-1-N03-2036,bq	model parameters </term> than similar <term>	phrase-based models	</term> . The <term> units of translation </term>	#3414 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,6-3-N03-2036,bq	During <term> decoding </term> , we use a <term>	block unigram model	</term> and a <term> word-based trigram language	#3434 During decoding, we use ablock unigram model and a word-based trigram language model.
model,7-1-N03-2036,bq	</term> . In this paper , we describe a <term>	phrase-based unigram model	</term> for <term> statistical machine translation	#3396 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,1-2-N03-2036,bq	<term> phrase-based models </term> . The <term>	units of translation	</term> are <term> blocks </term> - pairs of <term>	#3418 Theunits of translation are blocks - pairs of phrases.
other,10-5-N03-2036,bq	selection criteria </term> based on <term>	unigram	</term> counts and <term> phrase </term> length	#3471 We show experimental results on block selection criteria based onunigram counts and phrase length.
other,13-5-N03-2036,bq	based on <term> unigram </term> counts and <term>	phrase	</term> length . In this paper , we propose	#3474 We show experimental results on block selection criteria based on unigram counts andphrase length.
other,21-1-N03-2036,bq	</term> that uses a much simpler set of <term>	model parameters	</term> than similar <term> phrase-based models	#3410 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,4-4-N03-2036,bq	. During <term> training </term> , the <term>	blocks	</term> are learned from <term> source interval	#3448 During training, theblocks are learned from source interval projections using an underlying word alignment.
other,5-2-N03-2036,bq	<term> units of translation </term> are <term>	blocks	</term> - pairs of <term> phrases </term> . During	#3422 The units of translation areblocks - pairs of phrases.
other,5-5-N03-2036,bq	</term> . We show experimental results on <term>	block selection criteria	</term> based on <term> unigram </term> counts	#3466 We show experimental results onblock selection criteria based on unigram counts and phrase length.
other,8-4-N03-2036,bq	<term> blocks </term> are learned from <term>	source interval projections	</term> using an underlying <term> word alignment	#3452 During training, the blocks are learned fromsource interval projections using an underlying word alignment.
other,9-2-N03-2036,bq	</term> are <term> blocks </term> - pairs of <term>	phrases	</term> . During <term> decoding </term> , we	#3426 The units of translation are blocks - pairs ofphrases.
tech,1-3-N03-2036,bq	pairs of <term> phrases </term> . During <term>	decoding	</term> , we use a <term> block unigram model	#3429 Duringdecoding, we use a block unigram model and a word-based trigram language model.
tech,1-4-N03-2036,bq	trigram language model </term> . During <term>	training	</term> , the <term> blocks </term> are learned	#3445 Duringtraining, the blocks are learned from source interval projections using an underlying word alignment.
tech,11-1-N03-2036,bq	phrase-based unigram model </term> for <term>	statistical machine translation	</term> that uses a much simpler set of <term>	#3400 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.


	in Help