Performance Analysis of Different Smoothing Methods on n-grams for Statistical Machine Translation
A S M Mahmudul Hasan, Saria Islam, Muhammad Arifur Rahman · 2012
Smoothing techniques adjust the maximum likelihood estimate of probabilities to produce more accurate probabilities. This is one of the most important tasks while building a language model with a limited number of training data. Our main contribution of this paper is to analyze the performance of different smoothing techniques on n-grams. Here we considered three most widely-used smoothing algorithms for language modeling: Witten-Bell smoothing, Kneser-Ney smoothing, and Modified Kneser-Ney smoothing. For the