P15-1153 how to avoid such overlapping in phrase selection . A salience score is calculated
C86-1059 not in the context ) . Thus , phrase selection must be accounted for by partial
D10-1037 . The difficulty here is that phrase selection is highly context-dependent .
J87-3009 disambiguation in parsing , and for phrase selection in generation . Integration of
D08-1010 selection in word-based SMT and phrase selection in phrase-based SMT , rule selection
N10-1008 that the decision-tree - based phrase selection model can achieve rather reliable
J87-3009 is the impact of the context on phrase selection ? 1.2 ISSUES IN LANGUAGE ACQUISITION
P15-1153 constraints to realize our aim of phrase selection and new sentence construction
P15-1045 quasi-synchronous grammar ( QG ) to optimize phrase selection and surface realization preferences
D15-1012 linear programming for conducting phrase selection and merging simultaneously to
P15-1153 linear optimization for conducting phrase selection and merging simultaneously in
D11-1070 task intractable . 4.3 Indicator Phrase Selection Indicator phrases are sequences
P06-1002 different alignments change the phrase selection in the same MT system . 2 Related
P15-1153 our model also jointly conducts phrase selection and phrase merging ( new sentence
P15-1153 fourth terms . Meanwhile , the phrase selection is governed by a set of constraints
H93-1086 Examining methods for both statistical phrase selection and phrase weighting . For TREC
E89-1023 rhetorical formalism . Prepositional phrase selection is guided by keywords such as
P13-1002 which also affects the TM target phrase selection . This feature is a member of
P09-2046 Vietnamese language for the key phrase selection stage . We also explore NLP techniques
N10-1147 senses are highly lexicalized . 2.4 Phrase Selection Only the phrases that were tagged
hide detail