Graph-Based Collective Lexical Selection for Statistical Machine Translation

Lexical selection is of great importance to statistical machine translation. In this paper, we propose a graph-based framework for collective lexical selection. The framework is established on a translation graph that captures not only local associations between source-side content words and their target translations but also targetside global dependencies in terms of relatedness among target items. We also introduce a random walk style algorithm to collectively identify translations of sourceside content words that are strongly related in translation graph. We validate the effectiveness of our lexical selection framework on Chinese-English translation. Experiment results with large-scale training data show that our approach significantly improves lexical selection.