Paper Info
Title
Some novel applications of Explanation-Based Learning to parsing Lexicalized Tree-Adjoining Grammars
Abstract
In this paper we present some novel applications of Explanation-Based Learning (EBL) technique to parsing Lexicalized Tree-Adjoining grammars. The novel aspects are (a) immediate generalization of parses in the training set, (b) generalization over recursive structures and (c) representation of generalized parses as Finite State Transducers. A highly impoverished parser called a "stapler" has also been introduced. We present experimental results using EBL for different corpora and architectures to show the effectiveness of our approach.
Year
DOI
Venue
1995
10.3115/981658.981694
meeting of the association for computational linguistics
Keywords
Field
DocType
impoverished parser,different corpus,immediate generalization,lexicalized tree-adjoining grammars,lexicalized tree-adjoining grammar,finite state transducers,novel aspect,generalized parses,explanation-based learning,novel application,finite state transducer
Training set,Rule-based machine translation,Explanation-based learning,Computer science,Finite state,Natural language processing,Artificial intelligence,Parsing,Recursion
Journal
Volume
ISSN
Citations 
cmp-lg/9505023
ACL 1995
10
PageRank 
References 
Authors
0.97
11
2
Name
Order
Citations
PageRank
B. Srinivas115217.90
Aravind K. Joshi23479791.99