Dependency Graph-to-String Statistical Machine Translation
This addresses machine translation quality for languages with complex syntax, though it appears incremental as it builds on existing phrase-based and grammar-based approaches.
The paper tackles the problem of statistical machine translation by developing graph-based models that translate source dependency graphs into target strings, achieving significantly better performance than sequence- and tree-based baselines in Chinese-English and German-English experiments.
We present graph-based translation models which translate source graphs into target strings. Source graphs are constructed from dependency trees with extra links so that non-syntactic phrases are connected. Inspired by phrase-based models, we first introduce a translation model which segments a graph into a sequence of disjoint subgraphs and generates a translation by combining subgraph translations left-to-right using beam search. However, similar to phrase-based models, this model is weak at phrase reordering. Therefore, we further introduce a model based on a synchronous node replacement grammar which learns recursive translation rules. We provide two implementations of the model with different restrictions so that source graphs can be parsed efficiently. Experiments on Chinese--English and German--English show that our graph-based models are significantly better than corresponding sequence- and tree-based baselines.