Browse DORAS
Browse Theses
Latest Additions
Creative Commons License
Except where otherwise noted, content on this site is licensed for use under a:

QuEst for high quality machine translation

Bicici, Ergun (2015) QuEst for high quality machine translation. The Prague Bulletin of Mathematical Linguistics, 103 (1). pp. 43-64. ISSN 1804-0462

Full text available as:

PDF - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader


In this paper we describe the use of QuEst, a framework that aims to obtain predictions on the quality of translations, to improve the performance of machine translation (MT) systems without changing their internal functioning. We apply QuEst to experiments with: - multiple system translation ranking, where translations produced by different MT systems are ranked according to their estimated quality, leading to gains of up to 2.72 BLEU, 3.66 BLEUs, and 2.17 F1 points; - n-best list re-ranking, where n-best list translations produced by an MT system are re-ranked based on predicted quality scores to get the best translation ranked top, which lead to improvements on sentence NIST score by 0.41 points; - n-best list combination, where segments from an n-best list are combined using a lattice-based re-scoring approach that minimize word error, obtaining gains of 0.28 BLEU points; and - the ITERPE strategy, which attempts to identify translation errors regardless of prediction errors (ITERPE) and build sentence-specific SMT systems (SSSS) on the ITERPE sorted instances identified as having more potential for improvement, achieving gains of up to 1.43 BLEU, 0.54 F1, 2.9 NIST, 0.64 sentence BLEU, and 4.7 sentence NIST points in English to German over the top 100 ITERPE sorted instances.

Item Type:Article (Published)
Subjects:Computer Science > Machine translating
Computer Science > Computational linguistics
Computer Science > Machine learning
Computer Science > Artificial intelligence
DCU Faculties and Centres:Research Initiatives and Centres > Centre for Next Generation Localisation (CNGL)
DCU Faculties and Schools > Faculty of Engineering and Computing > School of Computing
Publisher:De Gruyter
Official URL:
Copyright Information:© 2015 De Gruyter
Use License:This item is licensed under a Creative Commons Attribution-NonCommercial-Share Alike 3.0 License. View License
Funders:SFI as part of the ADAPT CNGL Centre for Global Intelligent Content (, 07/CE/I1142), SFI for the project "Monolingual and Bilingual Text Quality Judgments with Translation Performance Prediction", European Commission through the QTLaunchPad FP7 project (, No: 296347)
ID Code:20649
Deposited On:15 Jun 2015 11:36 by Mehmet Ergun Bicici. Last Modified 08 Sep 2015 09:20

Download statistics

Archive Staff Only: edit this record