Advantages of System Combination for Spoken Language Translation | Combining Natural Language Processing Systems to Improve Machine Translation of Speech

Evgeny Matusov

ISBN 10: 3838120124 / ISBN 13: 9783838120126

Published by Südwestdeutscher Verlag für Hochschulschriften, 2015

About this Item

Advantages of System Combination for Spoken Language Translation | Combining Natural Language Processing Systems to Improve Machine Translation of Speech | Evgeny Matusov | Taschenbuch | 236 S. | Englisch | 2015 | Südwestdeutscher Verlag für Hochschulschriften | EAN 9783838120126 | Verantwortliche Person für die EU: preigu GmbH & Co. KG, Lengericher Landstr. 19, 49078 Osnabrück, mail[at]preigu[dot]de | Anbieter: preigu.

Seller Inventory # 107275222

Bibliographic Details

• Title: Advantages of System Combination for Spoken Language Translation | Combining Natural Language Processing Systems to Improve Machine Translation of Speech
• Publisher: Südwestdeutscher Verlag für Hochschulschriften
• Publication Date: 2015
• Language: English
• ISBN 10: 3838120124
• ISBN 13: 9783838120126
• Binding: Taschenbuch
• Condition: Neu
• Dimensions: 220W x 150H x 15D millimeters 220 millimeters width by 150 millimeters height by 15 millimeters depth
• Weight: 369 grams
• Seller catalogs:
  • Bücher

About this title

Synopsis

Automatic translation of spoken language is a challenging task that involves several natural language processing (NLP) software modules such as automatic speech recognition (ASR) and machine translation (MT) systems. In recent years, statistical approaches to both ASR and MT were proven to be effective on a large number of translation tasks. Yet the systems involved in speech translation are often developed independently of each other. This work explains how a significant improvement of speech translation quality can be obtained by enhancing the interface between various statistical NLP systems involved in the task of translating human speech. The whole pipeline is considered: ASR, automatic sentence segmentation, machine translation using several systems which take single best or multiple ASR hypotheses as input and employ different translation models, combination of different MT systems. The coupling between the various components is reached through combination of model scores and/or hypotheses as well as through development of new and modifications of existing algorithms to handle ambiguous input or to meet the constraints of the downstream components.

About the Author

Evgeny Matusov defended his Ph.D. in computer science from RWTH Aachen University, Germany in 2009. His research interest is machine translation of text and speech. He authored and co-authored more than 20 reviewed publications in international conferences, two journal publications, and received the ISCA Best Student Paper Award in 2005.