13 search results - page 1 / 3 » Learning Better Rule Extraction with Translation Span Alignm... |
ACL
2012
11 years 7 months ago
2012
This paper presents an unsupervised approach to learning translation span alignments from parallel data that improves syntactic rule extraction by deleting spurious word alignment...
EMNLP
2009
13 years 2 months ago
2009
We examine the problem of overcoming noisy word-level alignments when learning tree-to-string translation rules. Our approach introduces new rules, and reestimates rule probabilit...
COLING
2010
12 years 11 months ago
2010
This paper studies two methods for training hierarchical MT rules independently of word alignments. Bilingual chart parsing and EM algorithm are used to train bitext correspondenc...
EMNLP
2009
13 years 2 months ago
2009
Current statistical machine translation systems usually extract rules from bilingual corpora annotated with 1-best alignments. They are prone to learn noisy rules due to alignment...
ACL
2010
13 years 2 months ago
2010
We present cdec, an open source framework for decoding, aligning with, and training a number of statistical machine translation models, including word-based models, phrase-based m...