Title :
Dependency Parsing on Source Language with Reordering Information in SMT
Author :
Lei Chen ; Miao Li ; Miantao He ; Hui Liu
Author_Institution :
Inst. of Intell. Machines, Hefei, China
Abstract :
In statistical machine translation, many translation errors may easily occur especially when the word orders are very different between source language and target language, especially with asymmetric morphological structures. The paper investigates combining a rule-based reordering model with conventional dependency parsing at the source side, which can alleviate both the asymmetry of morphological structures and the word orders between source language and target language. Experiments show that this method can improve the performance of the statistical machine translation system.
Keywords :
computational linguistics; grammars; knowledge based systems; language translation; natural language processing; SMT; asymmetric morphological structures; dependency parsing; reordering information; rule-based reordering model; source language; statistical machine translation system; target language; translation errors; Educational institutions; Grammar; Morphology; NIST; Pragmatics; Syntactics; Training; dependency Parsing; machine translation; source-side Reordering;
Conference_Titel :
Asian Language Processing (IALP), 2012 International Conference on
Conference_Location :
Hanoi
Print_ISBN :
978-1-4673-6113-2
Electronic_ISBN :
978-0-7695-4886-9
DOI :
10.1109/IALP.2012.35