Pre-Reordering for Machine Translation Using Transition-Based Walks on Dependency Parse Trees

Antonio Miceli Barone, Giuseppe Attardi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We propose a pre-reordering scheme to improve the quality of machine translation by permuting the words of a source sentence to a target-like order. This is accomplished as a transition-based system that walks on the dependency parse tree of the sentence and emits words in target-like order, driven by a classifier trained on a parallel corpus. Our system is capable of generating arbitrary permutations up to flexible constraints determined by the choice of the classifier algorithm and input features.
Original languageEnglish
Title of host publicationProceedings of the Eighth Workshop on Statistical Machine Translation
PublisherAssociation for Computational Linguistics (ACL)
Pages164-169
Number of pages6
Publication statusPublished - 2013
EventACl 2013 Eighth Workshop on Statistical Machine Translation - Sofia, Bulgaria
Duration: 8 Aug 20139 Aug 2013
http://www.statmt.org/wmt13/

Workshop

WorkshopACl 2013 Eighth Workshop on Statistical Machine Translation
Abbreviated titleWMT13
Country/TerritoryBulgaria
CitySofia
Period8/08/139/08/13
Internet address

Fingerprint

Dive into the research topics of 'Pre-Reordering for Machine Translation Using Transition-Based Walks on Dependency Parse Trees'. Together they form a unique fingerprint.

Cite this