tech,25-2-H01-1041,bq meaning representation </term> called a <term> semantic frame </term> . The key features of the <term>
measure(ment),19-3-H01-1058,bq performance </term> ( typically , <term> word or semantic error rate </term> ) from a list of <term>
other,20-2-N03-1012,bq hypotheses ( SRH ) </term> in terms of their <term> semantic coherence </term> . We conducted an <term>
other,10-1-P03-1009,bq <term> clustering </term> in inducing <term> semantic verb classes </term> from undisambiguated
other,6-2-P03-1068,bq backbone of the <term> annotation </term> are <term> semantic roles </term> in the <term> frame semantics
tech,13-4-P03-1068,bq </term> and <term> ambiguity </term> in <term> semantic annotation </term> . We investigate the <term>
human agreement </term> . Motivated by this semantic criterion we analyze the empirical quality
other,8-3-N04-1024,bq </term> of <term> sentences </term> based on <term> semantic similarity measures </term> and <term> discourse
tech,16-1-I05-5003,bq related to the task of <term> sentence-level semantic equivalence classification </term> . This
other,25-2-I05-5003,bq <term> classifiers </term> to predict <term> semantic equivalence </term> and <term> entailment </term>
other,13-1-P06-1052,bq problem </term> : Given an <term> underspecified semantic representation ( USR ) </term> of a <term>
other,6-1-T78-1031,bq performing <term> inference </term> in <term> semantic networks </term> are presented and compared
other,8-5-T78-1031,bq rules </term> can be constructed in a <term> semantic network </term> using a variant of a <term>
other,1-4-P82-1035,bq being described . These <term> syntactic and semantic expectations </term> can be used to figure
other,1-3-P84-1047,bq </term> are grouped together . Like <term> semantic grammar </term> , this allows easy exploitation
other,25-3-C88-1007,bq obviating the need for answers to <term> semantic questions </term> that we do not yet have
other,31-1-C90-3045,bq </term> , for instance , to the task of <term> semantic interpretation </term> or <term> automatic
other,3-1-C90-3063,bq defeasibility </term> . Manual acquisition of <term> semantic constraints </term> in broad domains is very
other,8-3-C90-3063,bq these <term> statistics </term> reflect <term> semantic constraints </term> and thus are used to
other,18-6-C90-3063,bq statistics </term> indeed reflect the <term> semantic constraints </term> and thus provide a basis
hide detail