Statistical Machine Translation

View Sample PDF

Author(s): Lucia Specia (University of Sheffield, UK)
Copyright: 2014
Pages: 35
Source title: Computational Linguistics: Concepts, Methodologies, Tools, and Applications
Source Author(s)/Editor(s): Information Resources Management Association (USA)
DOI: 10.4018/978-1-4666-6042-7.ch043

Keywords: Computational Linguistics / Computer Science & IT / Digital Communications / Information Science Reference

Purchase

View Statistical Machine Translation on the publisher's website for pricing and purchasing information.

Abstract

Statistical Machine Translation (SMT) is an approach to automatic text translation based on the use of statistical models and examples of translations. SMT is the current dominant research paradigm for machine translation and has been attracting significant commercial interest in recent years. In this chapter, the authors introduce the rationale behind SMT, describe the currently leading approach (phrase-based SMT), and present a number of emerging approaches (tree-based SMT, discriminative SMT). They also present popular metrics to evaluate the performance of SMT systems and discuss promising research directions in the field.

The IRMA Community

Research IRM

Statistical Machine Translation

Purchase

Abstract

Related Content

IRMA Sponsors