Sciweavers

4 search results - page 1 / 1
» Forest-guided Supertagger Training
Sort
View
COLING
2010
12 years 12 months ago
Forest-guided Supertagger Training
Supertagging is an important technique for deep syntactic analysis. A supertagger is usually trained independently of the parser using a sequence labeling method. This presents an...
Yao-zhong Zhang, Takuya Matsuzaki, Jun-ichi Tsujii
ACL
2010
13 years 2 months ago
Faster Parsing by Supertagger Adaptation
We propose a novel self-training method for a parser which uses a lexicalised grammar and supertagger, focusing on increasing the speed of the parser rather than its accuracy. The...
Jonathan K. Kummerfeld, Jessika Roesner, Tim Dawbo...
ACL
2010
13 years 2 months ago
Minimized Models and Grammar-Informed Initialization for Supertagging with Highly Ambiguous Lexicons
We combine two complementary ideas for learning supertaggers from highly ambiguous lexicons: grammar-informed tag transitions and models minimized via integer programming. Each st...
Sujith Ravi, Jason Baldridge, Kevin Knight
EMNLP
2004
13 years 6 months ago
Object-Extraction and Question-Parsing using CCG
Accurate dependency recovery has recently been reported for a number of wide-coverage statistical parsers using Combinatory Categorial Grammar (CCG). However, overall figures give...
Stephen Clark, Mark Steedman, James R. Curran