Multilingual machine translation of closed captions for digital television with dynamic dictionary adaptation

Authors:
Sanghwa Yuh;Jungyun Seo
Affiliations:
School of Computer and Information, Kyungin Women's College, Incheon, Korea;Department of Computer Science and Interdisciplinary Program of Integrated Biotechnology, Sogang University, Seoul, Korea
Venue:
ICCPOL'06 Proceedings of the 21st international conference on Computer Processing of Oriental Languages: beyond the orient: the research challenges ahead
Year:
2006

Citing 5
Cited 0

Machine Translation of Closed Captions

Machine Translation
Automatic evaluation of summaries using N-gram co-occurrence statistics

NAACL '03 Proceedings of the 2003 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology - Volume 1
Automatic extraction of named entity translingual equivalence based on multi-feature cost minimization

MultiNER '03 Proceedings of the ACL 2003 workshop on Multilingual and mixed-language named entity recognition - Volume 15
Multilingual Closed Caption Translation System for Digital Television

IEICE - Transactions on Information and Systems
Pre-processing closed captions for machine translation

EmbedMT '00 ANLP-NAACL 2000 Workshop: Embedded Machine Translation Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we present a multilingual machine translation system for closed captions for digital television. To cope with frequent appearance of unregistered words and the articles of multiple domains as in TV news program, we propose a Dynamic Dictionary Adaptation method. We adopted live resources of multilingual Named Entities and their translingual equivalences from Web sites of daily news, providing multilingual daily news in Chinese, English, Japanese and Korean. We also utilize Dynamic Domain Identification for automatic dictionary stacking. With these integrated approaches, we obtained average translation quality enhancement of 0.5 in Mean Opinion Score (MOS) for Korean-to-Chinese. We also had 0.5 and 0.1 average enhancement for Korean-English and Korean-Japanese, respectively. The average enhancement is 0.37, which means almost a third level up to the next higher MOS scale.