measure(ment),20-1-P05-1039,ak suffix analysis </term> to achieve a <term> labelled bracket F-score </term> of 76.2 , higher than previously
tech,16-2-P05-1039,ak use of <term> smoothing </term> in an <term> unlexicalized parser </term> allows us to better examine the interplay
tech,7-1-P05-1039,ak </term> . In this paper , we present an <term> unlexicalized parser </term> for <term> German </term> which employs
tech,15-1-P05-1039,ak which employs <term> smoothing </term> and <term> suffix analysis </term> to achieve a <term> labelled bracket
tech,26-2-P05-1039,ak better examine the interplay between <term> smoothing </term> and parsing results . The applicability
tech,13-1-P05-1039,ak for <term> German </term> which employs <term> smoothing </term> and <term> suffix analysis </term> to
other,10-1-P05-1039,ak <term> unlexicalized parser </term> for <term> German </term> which employs <term> smoothing </term>
measure(ment),5-2-P05-1039,ak corpus </term> . In addition to the high <term> accuracy </term> of the model , the use of <term> smoothing
tech,13-2-P05-1039,ak accuracy </term> of the model , the use of <term> smoothing </term> in an <term> unlexicalized parser </term>
lr-prod,33-1-P05-1039,ak previously reported results on the <term> NEGRA corpus </term> . In addition to the high <term> accuracy
hide detail