D11-1106 ( Papineni et al. , 2002 ) for string comparison . Whilst BLEU is not an ideal
A88-1011 consists in applying a general string comparison technique to phonological codes
E95-1009 resulting metric was called feature string comparison . It could be argued that it
E95-1009 simplest technique used was phone string comparison . In this approach , all operations
D12-1039 generated , re-ranking based on string comparison is much faster . We only include
D11-1144 values , we explore several fuzzy string comparison algorithms and found n-gram substring
D11-1144 attribute values , we explore several string comparison algorithms and found n-gram substring
E09-1097 is uniform for all words . The string comparison task and its associated metrics
D12-1113 just m , which is identical to string comparison features already existing in
E95-1010 the distributions for ordered string comparisons and number comparisons , were
E95-1009 shows that the approaches based on string comparisons of the phonetic transcriptions
E95-1009 agglomerative clustering of phonetic string comparison distances is applied to Gaelic
E06-2015 feature , as it solely relies on string comparison and acronym string matching .
E09-1097 regenerated , as measured by any string comparison method : in our case , using
E95-1009 all-word vs. same-word feature string comparisons . All of these distance matrices
E95-1009 distance matrix computed by phonetic string comparison , and indeed the top-level topologies
E95-1010 measures , hard matching of numbers , string comparisons and n-gram co-occurrence matching
J01-4004 strings before performing the string comparison . Therefore , the license matches
C04-1013 can be compared naively with m20 string comparisons or much more e ciently using
A88-1011 speed , is that it is a general string comparison technique which is not biased
hide detail