Title: SyMGiza++: Symmetrized Word Alignment Models for Statistical Machine Translation
Abstract: SyMGiza++ — a tool that computes symmetric word alignment models with the capability to take advantage of multi-processor systems — is presented. A series of fairly simple modifications to the original IBM/Giza++ word alignment models allows to update the symmetrized models between chosen iterations of the original training algorithms. We achieve a relative alignment quality improvement of more than 17% compared to Giza++ and MGiza++ on the standard Canadian Hansards task, while maintaining the speed improvements provided by the capability of parallel computations of MGiza++. Furthermore, the alignment models are evaluated in the context of phrase-based statistical machine translation, where a consistent improvement measured in BLEU scores can be observed when SyMGiza++ is used instead of Giza++ or MGiza++.
Publication Year: 2012
Publication Date: 2012-01-01
Language: en
Type: book-chapter
Indexed In: ['crossref']
Access and Citation
Cited By Count: 47
AI Researcher Chatbot
Get quick answers to your questions about the article from our AI researcher chatbot