Language Model Adaptation in Machine Translation from Speech

This paper investigates the use of several language model adaptation techniques applied to the task of machine translation from Arabic broadcast speech. Unsupervised and discriminative approaches slightly outperform the traditional perplexity-based optimization technique. Language model adaptation,...

Full description

Saved in:
Bibliographic Details
Main Authors: Bulyko, I., Matsoukas, S., Schwartz, R., Nguyen, L., Makhoul, J.
Format: Conference Proceeding
Language:English
Subjects:
Adaptation model
Broadcast technology
Broadcasting
Decoding
domain adaptation
Interpolation
language modeling
Natural languages
Power measurement
Power system modeling
Speech recognition
Speech translation
Testing
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper investigates the use of several language model adaptation techniques applied to the task of machine translation from Arabic broadcast speech. Unsupervised and discriminative approaches slightly outperform the traditional perplexity-based optimization technique. Language model adaptation, when used for n-best rescoring, improves machine translation performance by 0.3-0.4 BLEU and reduces translation edit rate (TER) by 0.2-0.5% compared to an unadapted LM.
ISSN:1520-6149
2379-190X
DOI:10.1109/ICASSP.2007.367177