E09-3005 first instantiation of SCL for parse disambiguation indeed shows promising results
C96-1061 Disambiguation method . The Statistical Parse Disambiguation method makes use of the three
N10-1002 for unknown word handling . The parse disambiguation model we use is also trained
E09-3005 original SCL algorithm , applied to parse disambiguation . Of course , our results are
E09-3005 semi-supervised domain adaptation for parse disambiguation . We examine the effectiveness
C96-1061 predictions to the problem of parse disambiguation . This work has been carried
E09-3005 problem at hand . For the task of parse disambiguation based on a conditional model
C96-1061 trees , which are then used for parse disambiguation . The resuiting score is called
P07-1121 syntax-based SMT for lexical learning and parse disambiguation . The result is a robust semantic
C02-2025 constructions is very helpful for parse disambiguation . Method Task tag sel . parse
C02-2025 to build and test systems for parse disambiguation . As a component , we build a
D11-1073 predictive of coreference ; in parse disambiguation , the syntactic head of a noun
P08-1037 semantic features can enhance parse disambiguation . This paper shows that semantic
P08-2048 substantially beneficial to the parse disambiguation task . 1 Introduction Recent
P03-1054 results on the utility of PCFGs for parse disambiguation and language modeling were somewhat
E09-3005 Structural Correspondence Learning for Parse Disambiguation </title> Barbara Plank Abstract
E09-3005 , aligns well with the task of parse disambiguation : we first parse the unlabeled
C96-1061 ran - domly , and a Statistical Parse Disambiguation method . The Statistical Parse
J13-4006 role labeling and for syntactic parse disambiguation , and therefore the corresponding
C02-2025 a Verbmobil corpus they report parse disambiguation accuracy of 58.7 % given a baseline
hide detail