Language Model Adaptation in Machine Translation from Speech

Author

Bulyko, Ivan ; Matsoukas, Spyros ; Schwartz, R. ; Nguyen, L. ; Makhoul, John

Author_Institution

BBN Technol., Cambridge, MA, USA

Volume

fYear

2007

fDate

15-20 April 2007

Abstract

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.

Keywords

language translation; natural language processing; speech processing; Arabic broadcast speech; discriminative approaches; language model adaptation; machine translation; n-best rescoring; unsupervised approach; Adaptation model; Broadcast technology; Broadcasting; Decoding; Interpolation; Natural languages; Power measurement; Power system modeling; Speech recognition; Testing; Speech translation; domain adaptation; language modeling;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech and Signal Processing, 2007. ICASSP 2007. IEEE International Conference on

Conference_Location

Honolulu, HI

ISSN

1520-6149

Print_ISBN

1-4244-0727-3

Type

conf

DOI

10.1109/ICASSP.2007.367177

Filename

4218051

Link To Document

https://search.isc.ac/dl/search/defaultta.aspx?DTC=49&DC=2700822