Machine Translation with Minimal Reliance on Parallel Resources
Buch in deiner Nähe kaufen
Beschreibung
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). 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. Additionally, a free-to-use code is available, that allows the creation of new MT systems. 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.
Introduces a novel language-independent method for developing Machine Translation (MT) systems
Includes various experiments and comparisons to other MT systems
Provides a detailed presentation of the methodology principles and system architecture
Introduces a novel language-independent method for developing Machine Translation (MT) systems Includes various experiments and comparisons to other MT systems Provides a detailed presentation of the methodology principles and system architecture? Includes supplementary material: sn.pub/extras
Autor*in
George Tambouratzis
Themen in »Machine Translation with Minimal Reliance on Parallel Resources«
MT portability to new language pairs Machine learning methods Machine translation (MT) Non-reliance on expensive resources Statistical methods for language processing Pattern recognition Applied linguistics Natural language processing