Learning Better Rule Extraction with Translation Span Alignment

This paper presents an unsupervised approach to learning translation span alignments from parallel data that improves syntactic rule extraction by deleting spurious word alignment links and adding new valuable links based on bilingual translation span correspondences. Experiments on Chinese-English translation demonstrate improvements over standard methods for tree-to-string and tree-to-tree translation.

• Type: Journal
• Year: 2012
• Where: ACL
• Authors: Jingbo Zhu, Tong Xiao, Chunliang Zhang
• Keywords: ACL 2012, Bilingual Translation, Computational Linguistics, Unsupervised Approach, Word Alignment