Since sub-sentential alignment is critically important to the translation quality of an Example-Based Machine Translation (EBMT) system, which operates by finding and combining phrase-level matches against the training examples, we developed a new alignment algorithm for the purpose of improving the EBMT system's performance. This new Symmetric Probabilistic Alignment (SPA) algorithm treats the source and target languages in a symmetric fashion.
We describe our basic algorithm and its primary extensions that enable use of surrounding context, and of positional preference information, compare its alignment accuracy with IBM Model 4, and report on experiments in which either IBM Model 4 or SPA alignments are substituted for the aligner currently built into the EBMT system. Both Model 4 and SPA are significantly better than the internal aligner.
Then we extend SPA to exploit external alignment information from Moses and to output non-contiguous target phrases. We also alter SPA so that the weights for its feature scores are tuned using minimum error rate training. Our experiments show that exploiting external alignment information and non-contiguous alignment are helpful for SPA in the EBMT system.
Even with these improvements, however, SPA still could not properly deal with systematic translation for insertion or deletion words between two distant languages. Therefore, we attempt to alleviate this problem by using syntactic chunks as translation units. To do so, we developed a new chunk alignment algorithm that exploits word alignment information to align chunks. Then we integrated a chunk-based translation component based on the chunk alignment into the EBMT system that uses SPA for phrasal alignment. We show that the chunk alignment performs significantly better than the baseline system that aligns two chunks if any word pair of the two chunks has word alignment link. We also demonstrate that the system with chunk-based translation is significantly better than the baseline EBMT system with SPA in translation quality.
|School:||Carnegie Mellon University|
|School Location:||United States -- Pennsylvania|
|Source:||DAI-B 74/01(E), Dissertation Abstracts International|
|Subjects:||Information Technology, Artificial intelligence, Computer science|
|Keywords:||Machine translation, Symmetric probabilistic alignment|
Copyright in each Dissertation and Thesis is retained by the author. All Rights Reserved
The supplemental file or files you are about to download were provided to ProQuest by the author as part of a
dissertation or thesis. The supplemental files are provided "AS IS" without warranty. ProQuest is not responsible for the
content, format or impact on the supplemental file(s) on our system. in some cases, the file type may be unknown or
may be a .exe file. We recommend caution as you open such files.
Copyright of the original materials contained in the supplemental file is retained by the author and your access to the
supplemental files is subject to the ProQuest Terms and Conditions of use.
Depending on the size of the file(s) you are downloading, the system may take some time to download them. Please be