## Why does it matter?
- supportive facts are complex to learn
- even for humans
-- evaluating a working approach with new data is necessary to proove it
+- evaluating a working approach with new data is necessary to prove it
- collecting new datasets allows more precise evaluation of new models
-## research questions
+## Research Questions
- How can we transform real life/industry data sets to use in deep learning?
-- How well perform current politeness control mechanism on real life data sets?
-- How well perform current politeness control mechanism on distant language pairs?
+- How well do current politeness control mechanism perform on real life data sets?
+- How well do current politeness control mechanism perform on distant language pairs?
+
- How big is the impact of automated tone labeling in comparison to manual labeling?