Machine Translation with Lattices and Forests

Traditional 1-best translation pipelines suffer a major drawback: the errors of 1best 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 lattice and forest into a single tree-to-string system, and explore the algorithms of lattice parsing, lattice-forest-based rule extraction and decoding. More importantly, our model takes into account all the probabilities of different steps, such as segmentation, 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 show an improvement of +0.9 BLEU points over a state-of-the-art forest-based baseline.

• Type: Journal
• Year: 2010
• Where: COLING
• Authors: Haitao Mi, Liang Huang, Qun Liu
• Keywords: COLING 2010, Computational Linguistics, Lattice-forest-based Rule Extraction, Major Drawback, State-of-the-art Forest-based Baseline