Sciweavers

Share
ACL
2009

Improving Tree-to-Tree Translation with Packed Forests

10 years 9 months ago
Improving Tree-to-Tree Translation with Packed Forests
Current tree-to-tree models suffer from parsing errors as they usually use only 1best parses for rule extraction and decoding. We instead propose a forest-based tree-to-tree model that uses packed forests. The model is based on a probabilistic synchronous tree substitution grammar (STSG), which can be learned from aligned forest pairs automatically. The decoder finds ways of decomposing trees in the source forest into elementary trees using the source projection of STSG while building target forest in parallel. Comparable to the state-of-the-art phrase-based system Moses, using packed forests in tree-to-tree translation results in a significant absolute improvement of 3.6 BLEU points over using 1-best trees.
Yang Liu, Yajuan Lü, Qun Liu
Added 16 Feb 2011
Updated 16 Feb 2011
Type Journal
Year 2009
Where ACL
Authors Yang Liu, Yajuan Lü, Qun Liu
Comments (0)
books