W06-1710 which has impact on the results of distance measurement . But the computational complexity
W06-1710 another class of algorithms for distance measurement which are based on sequence alignments
W06-3201 metrics to arrive at the CPP phoneme distance measurement . Since the three distances are
H94-1025 . In this case , the semantic distance measurement algorithm helps to determine
N13-1028 Levenshtein distance and average pitch distance measurements . The diagrams provide visual
N07-1068 parameter that controls the impact of distance measurement . dist ( ( 7 ) TSub , TSub )
A94-1007 semantic taxonomy and the semantic distance measurement algorithm ( Knight , 1993 ; Okumura
W06-1710 good balance between accurate distance measurement of trees and computational complexity
W06-3201 2005 ) . We base our phonetic distance measurement on articulatory features because
P15-2082 books . Their method relies on the distance measurement to increase the precision and
W06-1108 for the unnormalized string edit distance measurements between 15 Norwegian di - alects
W06-1710 performances . Next , we perform pairwise distance measurements of the DOM-trees using the set
W06-1108 found unnormalized string edit distance measurements superior to normalized ones in
W05-1011 complexity , we consider the number of distance measurements as these dominate the computation
H94-1025 designed . By using the semantic distance measurement algorithm , one matching degree
H94-1025 three viewpoints . 1 . Semantic distance measurement To reduce the number of open
N07-1068 of subsequence length and the distance measurement . We randomly select 100 questions
W09-0701 the different languages ; such distance measurements are likely to be important for
W06-3201 used Bhattacharyya metric for the distance measurement ( Mak and Barnard 1996 ) . It
S15-2002 similarity with those alignments , and distance measurements on pooled latent semantic features
hide detail