Induction of probabilistic synchronous tree-insertion grammars for machine translation.

DSpace/Manakin Repository

Induction of probabilistic synchronous tree-insertion grammars for machine translation.

Citable link to this page

 

 
Title: Induction of probabilistic synchronous tree-insertion grammars for machine translation.
Author: Nesson, Rebecca; Rush, Alexander; Shieber, Stuart ORCID  0000-0002-7733-8195

Note: Order does not necessarily reflect citation order of authors.

Citation: Rebecca Nesson, Stuart M. Shieber, and Alexander Rush. Induction of probabilistic synchronous tree-insertion grammars for machine translation. In Proceedings of the 7th Conference of the Association for Machine Translation in the Americas (AMTA 2006), Boston, Massachusetts, 8-12 August 2006.
Full Text & Related Files:
Abstract: The more expressive and flexible a base formalism for machine translation is, the less efficient parsing of it will be. However, even among formalisms with the same parse complexity, some formalisms better realize the desired characteristics for machine translation formalisms than others. We introduce a particular formalism, probabilistic synchronous treeinsertion grammar (PSTIG) that we argue satisfies the desiderata optimally within the class of formalisms that can be parsed no less efficiently than context-free grammars and demonstrate that it outperforms state-of-the-art word-based and phrasebased finite-state translation models on training and test data taken from the EuroParl corpus (Koehn, 2005). We then argue that a higher level of translation quality can be achieved by hybridizing our induced model with elementary structures produced using supervised techniques such as those of Groves et al. (2004).
Published Version: http://www.mt-archive.info/AMTA-2006-Nesson.pdf
Terms of Use: This article is made available under the terms and conditions applicable to Other Posted Material, as set forth at http://nrs.harvard.edu/urn-3:HUL.InstRepos:dash.current.terms-of-use#LAA
Citable link to this page: http://nrs.harvard.edu/urn-3:HUL.InstRepos:2261232
Downloads of this work:

Show full Dublin Core record

This item appears in the following Collection(s)

 
 

Search DASH


Advanced Search
 
 

Submitters