Cross-language Projection of Dependency Trees for Tree-to-tree Machine Translation
Yu Chen Shen, Chenhui Chu, Fabien Cromierès, Sadao Kurohashi · Institutional Repositories DataBase (IRDB) · 2015
Syntax-based machine translation (MT) is an attractive approach for introducing addi-tional linguistic knowledge in corpus-based MT. Previous studies have shown that tree-to-string and string-to-tree translation mod-els perform better than tree-to-tree translation models since tree-to-tree models require two high quality parsers on the source as well as the target language side. In practice, high quality parsers for both languages are difficult to obtain and thus limit the translation quality. In this paper, we explore a method to transfer parse trees from the language side which has a high quality parser to the side which has a low quality parser to obtain transferred parse trees. We then combine the transferred parse trees with the original low quality parse trees. In our tree-to-tree MT experiments we have ob-served that the new combined trees lead to bet-ter performance in terms of BLEU score com-pared to when the original low quality trees and the transferred trees are used separately. 1