For Full-Text PDF, please login, if you are a member of IEICE,|
or go to Pay Per View on menu list, if you are a nonmember of IEICE.
Japanese Argument Reordering Based on Dependency Structure for Statistical Machine Translation
Chooi-Ling GOH Taro WATANABE Eiichiro SUMITA
IEICE TRANSACTIONS on Information and Systems
Publication Date: 2012/06/01
Online ISSN: 1745-1361
Print ISSN: 0916-8532
Type of Manuscript: PAPER
Category: Natural Language Processing
predicate-argument structure, reordering, paraphrasing, re-ranking, statistical machine translation,
Full Text: PDF(202.9KB)
>>Buy this Article
While phrase-based statistical machine translation systems prefer to translate with longer phrases, this may cause errors in a free word order language, such as Japanese, in which the order of the arguments of the predicates is not solely determined by the predicates and the arguments can be placed quite freely in the text. In this paper, we propose to reorder the arguments but not the predicates in Japanese using a dependency structure as a kind of reordering. Instead of a single deterministically given permutation, we generate multiple reordered phrases for each sentence and translate them independently. Then we apply a re-ranking method using a discriminative approach by Ranking Support Vector Machines (SVM) to re-score the multiple reordered phrase translations. In our experiment with the travel domain corpus BTEC, we gain a 1.22% BLEU score improvement when only 1-best is used for re-ranking and 4.12% BLEU score improvement when n-best is used for Japanese-English translation.