Overview

This book provides a unified view on a new methodology for Machine Translation (MT). This methodology extracts information from widely available resources (extensive monolingual corpora) while only assuming the existence of a very limited parallel corpus, thus having a unique starting point to Statistical Machine Translation (SMT).

Content and Experiments

In this book, a detailed presentation of the methodology principles and system architecture is followed by a series of experiments, where the proposed system is compared to other MT systems using a set of established metrics including BLEU, NIST, Meteor and TER.

Additional Resources

Additionally, a free-to-use code is available, that allows the creation of new MT systems.

Intended Audience and Prerequisites

The volume is addressed to both language professionals and researchers. Prerequisites for the readers are very limited and include a basic understanding of the machine translation as well as of the basic tools of natural language processing.