lr,15-2-C90-3063,bq co-occurrence patterns </term> in a large <term> corpus </term> . To a large extent , these <term>
lr,19-5-C90-3063,bq that were randomly selected from the <term> corpus </term> . The results of the experiment show
other,10-2-C90-3063,bq collecting <term> statistics </term> on <term> co-occurrence patterns </term> in a large <term> corpus </term> . To
other,10-5-C90-3063,bq references </term> of the <term> pronoun </term><term> it </term> in <term> sentences </term> that were
other,12-5-C90-3063,bq <term> pronoun </term><term> it </term> in <term> sentences </term> that were randomly selected from
other,13-6-C90-3063,bq show that in most of the cases the <term> cooccurrence statistics </term> indeed reflect the <term> semantic
other,16-3-C90-3063,bq </term> and thus are used to disambiguate <term> anaphora references </term> and <term> syntactic ambiguities </term>
other,18-6-C90-3063,bq statistics </term> indeed reflect the <term> semantic constraints </term> and thus provide a basis for a useful
other,19-3-C90-3063,bq <term> anaphora references </term> and <term> syntactic ambiguities </term> . The scheme was implemented by gathering
other,3-1-C90-3063,bq defeasibility </term> . Manual acquisition of <term> semantic constraints </term> in broad domains is very expensive
other,6-3-C90-3063,bq </term> . To a large extent , these <term> statistics </term> reflect <term> semantic constraints
other,6-4-C90-3063,bq scheme was implemented by gathering <term> statistics </term> on the output of other <term> linguistic
other,6-5-C90-3063,bq experiment was performed to resolve <term> references </term> of the <term> pronoun </term><term> it
other,8-2-C90-3063,bq automatic scheme </term> for collecting <term> statistics </term> on <term> co-occurrence patterns </term>
other,8-3-C90-3063,bq these <term> statistics </term> reflect <term> semantic constraints </term> and thus are used to disambiguate
other,9-5-C90-3063,bq resolve <term> references </term> of the <term> pronoun </term><term> it </term> in <term> sentences </term>
tech,12-4-C90-3063,bq statistics </term> on the output of other <term> linguistic tools </term> . An experiment was performed to
tech,28-6-C90-3063,bq thus provide a basis for a useful <term> disambiguation tool </term> . <term> Spelling-checkers </term> have
tech,4-2-C90-3063,bq expensive . This paper presents an <term> automatic scheme </term> for collecting <term> statistics </term>
hide detail