Detailed Information

Cited 0 time in webofscience Cited 0 time in scopus
Metadata Downloads

Estimating Translation Probabilities Considering Semantic Recoverabillity of Phrase Retranslation

Authors
Lee, Hyoung-GyuKim, Min-JeongQuan, YingXiuRim, Hae-ChangPark, So-Youne
Issue Date
Mar-2012
Publisher
IEICE-INST ELECTRONICS INFORMATION COMMUNICATIONS ENG
Keywords
statistical machine translation; phrase translation probability; semantic recoverability; phrase retranslation
Citation
IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, v.E95D, no.3, pp.897 - 901
Indexed
SCOPUS
Journal Title
IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS
Volume
E95D
Number
3
Start Page
897
End Page
901
URI
https://scholar.korea.ac.kr/handle/2021.sw.korea/105336
DOI
10.1587/transinf.E95.D.897
ISSN
1745-1361
Abstract
The general method for estimating phrase translation probabilities consists of sequential processes: word alignment, phrase pair extraction, and phrase translation probability calculation. However, during this sequential process, errors may propagate from the word alignment step through the translation. probability calculation step. In this paper, we propose a new method for estimating phrase translation probabilities that reduce the effects of error propagation. By considering the semantic recoverability of phrase retranslation, our method identifies incorrect phrase pairs that have propagated from alignment errors. Furthermore, we define retranslation similarity which represents the semantic recoverability of phrase retranslation, and use this when computing translation probabilities. Experimental results show that the proposed phrase translation estimation method effectively prevents a PBSMT system from selecting incorrect phrase pairs, and consistently improves the translation quality in various language pairs.
Files in This Item
There are no files associated with this item.
Appears in
Collections
College of Informatics > Department of Computer Science and Engineering > 1. Journal Articles

qrcode

Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.

Altmetrics

Total Views & Downloads

BROWSE