A Categorization of Hiero Reordering Rules

We propose to classify the Hiero grammar into subcategories, each of which is characterized with a specific reordering pattern. The subcategories enable us to encourage certain reordering patterns across a language-pair with a proper mixture-weight, to build a better grammar representation for machine translation. The Hiero grammar is classified according to the positions and the relative orders of the non-terminals (variables) and lexical items: variables with lexical items defining their boundaries, and the monotone/nonmonotone nature. We propose to learn the mixture-weight in two simple ways, relying on minimum error rate training and maximum likelihood training, respectively. Improved translation results were obtained from a state-of-the-art Arabic-English Hiero system.

By: Bing Zhao

Published in: RC24910 in 2009


This Research Report is available. This report has been submitted for publication outside of IBM and will probably be copyrighted if accepted for publication. It has been issued as a Research Report for early dissemination of its contents. In view of the transfer of copyright to the outside publisher, its distribution outside of IBM prior to publication should be limited to peer communications and specific requests. After outside publication, requests should be filled only by reprints or legally obtained copies of the article (e.g., payment of royalties). I have read and understand this notice and am a member of the scientific community outside or inside of IBM seeking a single copy only.


Questions about this service can be mailed to reports@us.ibm.com .