In this work, we present a novel distortion model for an Arabic to English maximum entropy word aligner. In constrast to the distortion model of (Ittycheriah and Roukos, 2005), our model is integrated with the observation model allowing the parameters to be estimated jointly. To have more robust estimates, the distortion model is parametrized using linguistically motivated features such as segmentation and WordNet information. The resulting aligner gives significant improvements over a strong baseline on two different data sets. We also present preliminary work on a self-trained alignment model, which improves alignment quality even further.
By: Abhishek Arun; Abraham Ittycheriah
Published in: RC24584 in 2008
LIMITED DISTRIBUTION NOTICE:
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 .