N10-1040 prototype , we substitute all single-word translations in our dictionary1 . For each
E06-1006 reordering effects resulting from single-word translations of OOVs is to restrict the distortion
W10-3704 First , we check if there is a single-word translation in any of the target languages
W06-1609 often occurs that large number of single-word translation probabilities are left out of
W10-3308 field ( TRANS ) gives the default single-word translation ( or several such translations
P12-1103 is replaced by a phrase with a single-word translation . ( 3 ) Recovering omitted words
J00-2004 . How can we decide whether a single-word translation " matches " a phrasal translation
W03-0314 total accuracy , accuracies for single-word translation pairs only and for multi-word
W01-1411 coverage and accuracy are given for single-word translations only . According to the standard
W03-0314 a cause of poor performance in single-word translation pairs , since there is no mechanism
W03-0314 tokens that can be aligned by single-word translation pairs is not explicitly mentioned
W09-2404 experiment set-up : we are looking at single-word translations while the translation of a longer
W01-1411 Melamed 's published results on single-word translation , we show Table 2 , where both
H01-1033 covering many genres of English . All single-word translations are ordered by decreasing unigram
W10-3704 ( an MWE in one language has a single-word translation in another language ) as empirical
W01-1411 compounds differently from his work on single-word translation pairs , so we are not able to
W03-0314 include " not sure " ones for a single-word translation . Those are entries which are
W01-1411 our performance is quite good on single-word translations , with accuracy of around 80
W03-0314 by the similarity score . For single-word translation , we get 93-99 % accuracy at
A97-1050 in order to propose candidate single-word translations : once likely general usage terms
hide detail