Advantages of System Combination for Spoken Language Translation: Combining Natural Language Processing Systems to Improve Machine Translation of Speech - Couverture souple

Matusov, Evgeny

 
9783838120126: Advantages of System Combination for Spoken Language Translation: Combining Natural Language Processing Systems to Improve Machine Translation of Speech
Couverture souple
ISBN 10 : 3838120124 ISBN 13 : 9783838120126
Editeur : Südwestdeutscher Verlag für Hochschulschriften, 2010

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.

Les informations fournies dans la section « Synopsis » peuvent faire référence à une autre édition de ce titre.

Présentation de l'éditeur

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.

Biographie de l'auteur

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.

Les informations fournies dans la section « A propos du livre » peuvent faire référence à une autre édition de ce titre.

Éditeur
Südwestdeutscher Verlag für Hochschulschriften
Date d'édition
2010
Langue
anglais
ISBN 10 
3838120124
ISBN 13 
9783838120126
Reliure
Broché
Nombre de pages
236
Coordonnées du fabricant
non disponible
Personne responsable
non disponible