Login (DCU Staff Only)
Login (DCU Staff Only)

DORAS | DCU Research Repository

Explore open access research and scholarly works from DCU

Advanced Search

Using TERp to augment the system combination for SMT

Du, Jinhua orcid logoORCID: 0000-0002-3267-4881 and Way, Andy orcid logoORCID: 0000-0001-5736-5930 (2010) Using TERp to augment the system combination for SMT. In: AMTA 2010 - 9th Conference of the Association for Machine Translation in the Americas, 31 October - 4 November 2010, Denver, CO, USA.

Abstract
TER-Plus (TERp) is an extended TER evaluation metric incorporating morphology, synonymy and paraphrases. There are three new edit operations in TERp: Stem Matches, Synonym Matches and Phrase Substitutions (Para-phrases). In this paper, we propose a TERp-based augmented system combination in terms of the backbone selection and consensus decoding network. Combining the new properties of the TERp, we also propose a two-pass decoding strategy for the lattice-based phrase-level confusion network(CN) to generate the final result. The experiments conducted on the NIST2008 Chinese-to-English test set show that our TERp-based augmented system combination framework achieves significant improvements in terms of BLEU and TERp scores compared to the state-of-the-art word-level system combination framework and a TER-based combination strategy.
Metadata
Item Type:Conference or Workshop Item (Paper)
Event Type:Conference
Refereed:Yes
Subjects:Computer Science > Machine translating
DCU Faculties and Centres:Research Initiatives and Centres > Centre for Next Generation Localisation (CNGL)
Publisher:Association for Machine Translation in the Americas
Official URL:http://amta2010.amtaweb.org/AMTA/html/toc.htm
Use License:This item is licensed under a Creative Commons Attribution-NonCommercial-Share Alike 3.0 License. View License
ID Code:15806
Deposited On:06 Dec 2010 13:51 by Shane Harper . Last Modified 09 Nov 2018 15:55
Documents

Full text available as:

[thumbnail of Using_TERp_to_Augment_the_System_Combination_for_SMT.pdf]
Preview
PDF - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
184kB
Downloads

Downloads

Downloads per month over past year

Archive Staff Only: edit this record