Word sense disambiguation is an important intermediate stage for many natural language processing applications. The senses of an ambiguous word are the classification of usages for that specific word. This paper deals with the methodologies of determining the senses for a given word if they can not be obtained from an already available resource like WordNet. We offer a method that helps us to determine the sense boundaries gradually. In this method, first we decide on some features that are thought to be effective on the senses and divide the instances first into two, then according to the results of evaluations we continue dividing instances gradually. In a second method we use the pseudo words. We devise artificial words depending on some criteria and evaluate classification algorithms on these previously classified words. Keywords—Word sense disambiguation, sense determination, pseudo words, sense granularity.
[1]
Tanja Gaustad,et al.
Statistical Corpus-Based Word Sense Disambiguation: Pseudowords vs. Real Ambiguous Words
,
2001,
ACL.
[2]
Nancy Ide,et al.
Introduction to the Special Issue on Word Sense Disambiguation: The State of the Art
,
1998,
Comput. Linguistics.
[3]
C. Habel,et al.
Language
,
1931,
NeuroImage.
[4]
Preslav Nakov,et al.
Category-based Pseudowords
,
2003,
HLT-NAACL.
[5]
Dilek Z. Hakkani-Tür,et al.
Building a Turkish Treebank
,
2003
.
[6]
W. N. Locke,et al.
Machine Translation of Languages
,
1956
.
[7]
N. Cocchiarella,et al.
Situations and Attitudes.
,
1986
.