We examine the problem of overcoming noisy word-level alignments when learning tree-to-string translation rules. Our approach introduces new rules, and reestimates rule probabilit...
When machine translation (MT) knowledge is automatically constructed from bilingual corpora, redundant rules are acquired due to translation variety. These rules increase ambiguit...
In the "Sandglass" MT architecture, we identify the class of monosemous Japanese functional expressions and utilize it in the task of translating Japanese functional exp...
Taiji Nagasaka, Ran Shimanouchi, Akiko Sakamoto, T...
We present a framework for publishing relational data in XML with respect to a fixed DTD. In data exchange on the Web, XML views of relational data are typically required to confo...
Michael Benedikt, Chee Yong Chan, Wenfei Fan, Raje...
Current statistical machine translation systems usually extract rules from bilingual corpora annotated with 1-best alignments. They are prone to learn noisy rules due to alignment...