12 search results - page 1 / 3 » Discriminative Alignment Training without Annotated Data for... |
35
Voted
NAACL
2007
14 years 11 months ago
2007
EMNLP
2009
14 years 7 months ago
2009
Current statistical machine translation (SMT) systems are trained on sentencealigned and word-aligned parallel text collected from various sources. Translation model parameters ar...
ACL
2008
14 years 11 months ago
2008
Documents in languages such as Chinese, Japanese and Korean sometimes annotate terms with their translations in English inside a pair of parentheses. We present a method to extrac...
ACL
2006
14 years 11 months ago
2006
For many years, statistical machine translation relied on generative models to provide bilingual word alignments. In 2005, several independent efforts showed that discriminative m...
ACL
2010
14 years 8 months ago
2010
We present a simple yet powerful hierarchical search algorithm for automatic word alignment. Our algorithm induces a forest of alignments from which we can efficiently extract a r...