We present an experimental statistical tree-to-tree machine translation system based on the multi-bottom up tree transducer including rule extraction, tuning and decoding. Thanks to input parse forests and a “no pruning” strategy during decoding, the obtained translations are competitive. The drawbacks are a restricted coverage of 70% on test data, in part due to exact input parse tree matching, and a relatively high runtime. Advantages include easy redecoding with a different weight vector, since the full translation forests can be stored after the first decoding pass.
Paper
Full text
Exact Decoding with Multi Bottom-Up Tree Transducers
Semantic Scholar · Computer Science · 2015
Abstract
We present an experimental statistical tree-to-tree machine translation system based on the multi-bottom up tree transducer including rule extraction, tuning and decoding. Thanks to input parse forests and a “no pruning” strategy during decoding, the obtained translations are competitive. The drawbacks are a restricted coverage of 70% on test data, in part due to exact input parse tree matching, and a relatively high runtime. Advantages include easy redecoding with a different weight vector, since the full translation forests can be stored after the first decoding pass.