article · 2002
Binary Feature Classification for Word
Disambiguation In Statistical, Jesús Tomás, Francisco Casacuberta
Cited by 0Abstract and details only
Abstract
In statistical machine translation, there are many source words that can present different translations. The usual approach to disambiguating these words is to use a target language model. These models are based on local phenomena and in many cases are not capable of properly translating some of these words. To deal with this problem, a new approach is proposed that is based on the so-called naive Bayesian classifier. After a process of automatic selection of ambiguous words, an adequate binary feature set that maximizes the information gain is chosen. A Bayesian classifier can be used to choose the most adequate translation of a word, using this feature set. Experimental results on a parallel corpus (approximately 650,000 Spanish-Catalan sentence pairs) show the benefits that the proposed method can achieve.
Cite this paper
Statistical, D. I., Tomás, J., & Casacuberta, F. (2002). Binary Feature Classification for Word.
Statistical, Disambiguation In, et al. “Binary Feature Classification for Word.” 2002.
Statistical, Disambiguation In, Jesús Tomás, and Francisco Casacuberta. 2002. “Binary Feature Classification for Word.”
Statistical, D.I., Tomás, J. and Casacuberta, F. (2002) ‘Binary Feature Classification for Word’.
@article{statistical2002binary,
title = {{Binary Feature Classification for Word}},
author = {Statistical, Disambiguation In and Tomás, Jesús and Casacuberta, Francisco},
year = {2002}
}Made from the index record. Check names, capitalisation and page numbers against the paper. Need another style? AI for Research has over 10,000.