Paper: Machine Translation with Lattices and Forests

ACL ID C10-2096
Title Machine Translation with Lattices and Forests
Venue International Conference on Computational Linguistics
Session Poster Session
Year 2010

Traditional 1-best translation pipelines suffer a major drawback: the errors of 1- best outputs, inevitably introduced by each module, will propagate and accumulate along the pipeline. In order to alleviate this problem, we use compact structures, lattice and forest, in each module instead of 1-best results. We integrate both lat- tice and forest into a single tree-to-string system, and explore the algorithms of lat- tice parsing, lattice-forest-based rule ex- traction and decoding. More importantly, our model takes into account all the proba- bilities of different steps, such as segmen- tation, parsing, and translation. The main advantage of our model is that we can make global decision to search for the best segmentation, parse-tree and translation in one step. Medium-scale experiments s...