Generalizing Dependency Features for Opinion Mining

by Mahesh Joshi , Carolyn Penstein-rosé

Citations:

7 - 0 self

Datum	Value	Source
TITLE	Generalizing Dependency Features for Opinion Mining	SVM HeaderParse 0.2
AUTHOR NAME	Mahesh Joshi	SVM HeaderParse 0.2
AUTHOR AFFIL	1; Language Technologies Institute; 2; Human-Computer Interaction Institute; Carnegie Mellon University, Pittsburgh	SVM HeaderParse 0.2
AUTHOR ADDR	PA, USA	SVM HeaderParse 0.2
AUTHOR NAME	Carolyn Penstein-rosé	SVM HeaderParse 0.2
AUTHOR AFFIL	1; Language Technologies Institute; 2; Human-Computer Interaction Institute; Carnegie Mellon University, Pittsburgh	SVM HeaderParse 0.2
AUTHOR ADDR	PA, USA	SVM HeaderParse 0.2
ABSTRACT	We explore how features based on syntactic dependency relations can be utilized to improve performance on opinion mining. Using a transformation of dependency relation triples, we convert them into “composite back-off features ” that generalize better than the regular lexicalized dependency relation features. Experiments comparing our approach with several other approaches that generalize dependency features or ngrams demonstrate the utility of composite back-off features. 1	SVM HeaderParse 0.2
CITATIONS	11 found	ParsCit 1.0