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

DORAS | DCU Research Repository

Explore open access research and scholarly works from DCU

Advanced Search

Robust language pair-independent sub-tree alignment

Tinsley, John, Zhechev, Ventsislav, Hearne, Mary and Way, Andy orcid logoORCID: 0000-0001-5736-5930 (2007) Robust language pair-independent sub-tree alignment. In: Machine Translation Summit XI, 10-14 September, 2007, Copenhagen, Denmark.

Abstract
Data-driven approaches to machine translation (MT) achieve state-of-the-art results. Many syntax-aware approaches, such as Example-Based MT and Data-Oriented Translation, make use of tree pairs aligned at sub-sentential level. Obtaining sub-sentential alignments manually is time-consuming and error-prone, and requires expert knowledge of both source and target languages. We propose a novel, language pair-independent algorithm which automatically induces alignments between phrase-structure trees. We evaluate the alignments themselves against a manually aligned gold standard, and perform an extrinsic evaluation by using the aligned data to train and test a DOT system. Our results show that translation accuracy is comparable to that of the same translation system trained on manually aligned data, and coverage improves.
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 > National Centre for Language Technology (NCLT)
Publisher:European Association for Machine Translation
Official URL:http://www.mt-archive.info/MTS-2007-Tinsley.pdf
Use License:This item is licensed under a Creative Commons Attribution-NonCommercial-Share Alike 3.0 License. View License
Funders:Science Foundation Ireland, SFI 05/RF/CMS064
ID Code:15230
Deposited On:18 Feb 2010 14:18 by DORAS Administrator . Last Modified 16 Nov 2018 10:40
Documents

Full text available as:

[thumbnail of TinsleyEtAl_summit_07.pdf]
Preview
PDF - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
1MB
Downloads

Downloads

Downloads per month over past year

Archive Staff Only: edit this record