CORR
1999
Springer
13 years 4 months ago
1999
Springer
We present a technique which complements Hidden Markov Models by incorporating some lexicalized states representing syntactically uncommon words. 'Our approach examines the d...
ACL
1996
13 years 5 months ago
1996
Lexicalized Tree Adjoining Grammars have proved useful for NLP. However, numerous redundancy problems face LTAGs developers, as highlighted by Vijay-Shanker and Schabes (92). We p...
ACL
2000
13 years 5 months ago
2000
We discuss the advantages of lexicalized tree-adjoining grammar as an alternative to lexicalized PCFG for statistical parsing, describingthe induction of a probabilistic LTAG mode...
ACL
1998
13 years 5 months ago
1998
In this paper we view Lexicalized Tree Adjoining Grammars as the compilation of a tract and modular layer of linguistic description :the metagrammar (MG). MG provides a hierarchic...
ACL
2003
13 years 5 months ago
2003
We demonstrate that an unlexicalized PCFG can parse much more accurately than previously shown, by making use of simple, linguistically motivated state splits, which break down fa...
ACL
2006
13 years 5 months ago
2006
We present the implementation of a system which extracts not only lexicalized grammars but also feature-based lexicalized grammars from Korean Sejong Treebank. We report on some p...
CICLING
2005
Springer
13 years 6 months ago
2005
Springer
We use prior and boundary estimates as the approximation of outside probability and establish our beam thresholding strategies based on these estimates. Lexical items, e.g. head wo...