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

Comparing constituency and dependency representations for SMT phrase-extraction

Hearne, Mary and Ozdowska, Sylwia and Tinsley, John (2008) Comparing constituency and dependency representations for SMT phrase-extraction. In: TALN 2008 - la 15éme Conférence Annuelle sur le Traitement Automatique des Langues Naturelles, 9-13 June 2008, Avignon, France.

Full text available as:

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


We consider the value of replacing and/or combining string-based methods with syntax-based methods for phrase-based statistical machine translation (PBSMT), and we also consider the relative merits of using constituency-annotated vs. dependency-annotated training data. We automatically derive two subtree-aligned treebanks, dependency-based and constituency-based, from a parallel English–French corpus and extract syntactically motivated word- and phrase-pairs. We automatically measure PB-SMT quality. The results show that combining string-based and syntax-based word- and phrase-pairs can improve translation quality irrespective of the type of syntactic annotation. Furthermore, using dependency annotation yields greater translation quality than constituency annotation for PB-SMT.

Item Type:Conference or Workshop Item (Paper)
Event Type:Conference
Uncontrolled Keywords:PB-SMT; constituency annotation; dependency annotation; subtree-aligned parallel treebanks;
Subjects:Computer Science > Machine learning
DCU Faculties and Centres:Research Initiatives and Centres > National Centre for Language Technology (NCLT)
Official URL:
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, SFI 05/IN/1732
ID Code:15193
Deposited On:16 Feb 2010 14:48 by DORAS Administrator. Last Modified 27 Apr 2010 12:24

Download statistics

Archive Staff Only: edit this record