Publication - Conditional Random Fields versus template-matching in MT phrasing tasks involving sparse training data
RESEARCH

Conditional Random Fields versus template-matching in MT phrasing tasks involving sparse training data

Research Area:  
Other topics in Computer Science
    
Type:  
Journal article

 

Year: 2014
Authors: George Tambouratzis
Journal: Pattern Recognition Letters
Volume: in print
Number: in print
ISSN: 0167-8655
DOI: in print
Abstract:
This communication focuses on comparing the template-matching technique to established probabilistic approaches - such as Conditional Random Fields (CRF) - on a specific linguistic task, namely the phrasing of a sequence of words into phrases. This task represents a low-level parsing of the sequence into linguistically-motivated phrases. CRF represents the established method for implementing such a data-driven parser, while template-matching is a simpler method that is faster to train and operate. The two aforementioned techniques are compared here to determine the most suitable approach for extracting an accurate model.
[Bibtex]