Most of the best translation systems today are based on phrase translation pairs (i.e. “blocks”). The blocks are obtained from word alignment. In this paper, we use blocks to improve word alignment. Improved word alignment in turn leads to better inference of blocks. We propose two new probabilistic models and EM-based algorithms to estimate their parameters. The first model recovers IBM Model-1 as a special case. Both models outperform bidirectional alignments based on HMM or IBM Model-4: up to 10% absolute improvement in Chinese-English word alignment over GIZA Model-4 bidirectional alignment. Using blocks obtained from the proposed models, we also get statistically significant improvement in BLEU on NIST MT-03 test set.
By: Bing Zhao; Niyu Ge; Kishore Papineni
Published in: RC23491 in 2005
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 .