Bakarić, Nikola and Njavro, Jasmina and Ljubešić, Nikola. (2007). What Makes Sense? : Searching for Strong WSD Predictors in Croatian. In: 1. međunarodna znanstvena konferencija "The Future of Information Sciences: INFuture2007 – Digital Information and Heritage", 7.-9. studenoga 2007., Zagreb.
|
PDF
(English)
Download (319kB) | Preview |
Abstract
The goal of this research was to investigate and determine position of strong predictors for word sense disambiguation of Croatian nouns. Research was conducted using supervised learning methods and a corpus of around 70 million words. We have concluded that words in the immediate vicinity of an observed lexeme (1-5 words left and right) have the highest discriminative power. We have also measured the applicability and accuracy of the one-sense-per-discourse method and found it to be very successful as well as the impact of sentence boundaries which proved not to be a good criterion for selecting strong predictors.
Item Type: | Published conference work (Lecture) |
---|---|
Uncontrolled Keywords: | word sense disambiguation, Croatian language, strong predictors |
Subjects: | Information sciences > Social-humanistic informatics Information sciences > Natural language processing, lexicography and encyclopedic science |
Departments: | Department of Information Science |
Date Deposited: | 22 Feb 2017 08:36 |
Last Modified: | 22 Feb 2017 08:36 |
URI: | http://darhiv.ffzg.unizg.hr/id/eprint/7944 |
Actions (login required)
View Item |