Date of Original Version
Abstract or Description
Since subsentential 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 recently decided to develop a new alignment algorithm for the purpose of improving the EBMT system’s performance. Unlike most algorithms in the literature, this new Symmetric Probabilistic Alignment (SPA) algorithm treats the source and target languages in a symmetric fashion. In this paper, we describe our basic algorithm and some extensions for using context and positional 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 and SPA slightly outperforms Model 4 despite being handicapped by incomplete integration with EBMT.