A graph-based cross-lingual projection approach for spoken language understanding portability to a new language

The portability of spoken language understanding to a new language can be improved by the results of automatic translation. However, the translation errors can cause the falling-off in the quality of the target language system. This paper proposes a graph-based projection approach to improve the robustness against the translation errors in cross-lingual spoken language understanding. The experimental results show that our proposed approach can significantly improve the performances of the task in a new language.