@inproceedings{4247411f07064100bc19c1e04f24415b,
title = "Building up lexical sample dataset for Turkish word sense disambiguation",
abstract = "Word Sense Disambiguation (WSD) has become even more important research area in recent years with the widespread usage of Natural Language Processing (NLP) applications. WSD task has two variants: {"}Lexical Sample{"} and {"}All Words{"} approaches. Lexical Sample approach disambiguates the occurrences of a small sample of target words that were previously selected, while in the latter all the words in a piece of text are disambiguated. In the scope of this work, a Lexical Sample Dataset for Turkish has been prepared. As a first step, highly ambiguous words in Turkish have been selected. Collection of text samples for chosen words has been completed. Five taggers have annotated the word senses. This paper summarizes the step-by-step building-up process of a Lexical Sample Dataset in Turkish and presents the results of some experiments on it.",
keywords = "Feature Selection, Lexical Sample, Machine Learning, Natural Language Processing, Word Sense Disambiguation",
author = "Bahar Ilgen and E{\c s}ref Adali and Tantuǧ, \{A. C{\"u}neyd\}",
year = "2012",
doi = "10.1109/INISTA.2012.6247026",
language = "English",
isbn = "9781467314466",
series = "INISTA 2012 - International Symposium on INnovations in Intelligent SysTems and Applications",
booktitle = "INISTA 2012 - International Symposium on INnovations in Intelligent SysTems and Applications",
note = "International Symposium on INnovations in Intelligent SysTems and Applications, INISTA 2012 ; Conference date: 02-07-2012 Through 04-07-2012",
}