Record Details

Context-sensitive semantic smoothing using semantically relatable sequences

DSpace at IIT Bombay

View Archive Info
 
 
Field Value
 
Title Context-sensitive semantic smoothing using semantically relatable sequences
 
Creator VERMA, KS
BHATTACHARYYA, P
 
Description We propose a novel approach to context sensitive semantic smoothing by making use of an intermediate, "semantically light" representation for sentences, called Semantically Relatable Sequences (SRS). SRSs of a sentence are tuples of words appearing in the semantic graph of the sentence as linked nodes depicting dependency relations. In contrast to patterns based on consecutive words, SRSs make use of groupings of non-consecutive but semantically related words. Our experiments on TREC AP89 collection show that the mixture model of SRS translation model and Two Stage Language Model (TSLM) of Lafferty and Zhai achieves MAP scores better than the mixture-model of MultiWord Expression (MWE) translation model and TSLM. Furthermore, a system, which for each test query selects either the SRS or the MWE mixture model based on better query MAP score, shows significant improvements over the individual mixture models.
 
Publisher IJCAI-INT JOINT CONF ARTIF INTELL
 
Date 2011-10-25T16:10:43Z
2011-12-15T09:12:01Z
2011-10-25T16:10:43Z
2011-12-15T09:12:01Z
2009
 
Type Proceedings Paper
 
Identifier 21ST INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE (IJCAI-09), PROCEEDINGS,1580-1585
978-1-57735-426-0
http://dspace.library.iitb.ac.in/xmlui/handle/10054/15764
http://hdl.handle.net/100/2422
 
Source 21st Internation Joint Conference on Artifical Intelligence (IJCAI-09),Pasadena, CA,JUL 11-17, 2009
 
Language English