Home

About

Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network
FAQHELPSITE MAPCONTACT US


  Advanced Search  

 
A Memory-Based Approach to Learning Shallow Natural Language Patterns
 

Summary: A Memory-Based Approach to Learning Shallow
Natural Language Patterns
Shlomo Argamon-Engelson Ido Dagan
Yuval Krymolowski
Department of Mathematics and Computer Science
Bar-Ilan University
52900 Ramat Gan, Israel
fargamon,dagan,yuvalkg@cs.biu.ac.il
March 6, 1999
Abstract
Recognizing shallow linguistic patterns, such as basic syntactic relationships between words,
is a common task in applied natural language and text processing. The common practice for
approaching this task is by tedious manual de nition of possible pattern structures, often
in the form of regular expressions or nite automata. This paper presents a novel memory-
based learning method that recognizes shallow patterns in new text based on a bracketed
training corpus. The examples are stored as-is, in e cient data structures. Generalization is
performed on-line at recognition time by comparing subsequences of the new text to positive
and negative evidence in the corpus. This way, no information in the training is lost, as can
happen in other learning systems that construct a single generalized model at the time of
training. The paper presents experimental results for recognizing noun phrase, subject-verb

  

Source: Argamon, Shlomo - Department of Computer Science, Illinois Institute of Technology

 

Collections: Computer Technologies and Information Sciences