Translating Questions for Cross-Lingual QA

In this paper we investigate possibili-ties of the development of a task-specific translation component for cross-language question answering. We focus on the optimization of phrase-based SMT for models trained on very limited data re-sources. We also look at the combina-tion of such systems with another approach based on example-based MT with propor-tional analogies. In our experiments we could improve a strong baseline of a gen-eral purpose MT engine with more than 5 BLEU points.