- After reading the first three chapters: 
      * list the main parts/components/structures of the model. 
      * Is their creation dependent on other components?
   - Thinking about the scripts:
      * What is the main reason (the biggest advantage) of using scripts? What kind of information does it bring? (Hint: page 2, page 8)
      * The authors don't get the "knowledge" of scripts straightforwardly. How is that "knowledge" represented in the model and which (four) ways are used to get it?
   - In the last paragraph of Section 3, a method is described that enhances the robustness of the model (binarization of all association weights <latex>w^z_i</latex>). Answer one of the following questions (choose one):
      * Why does it work? (=> Why should it work best?)
      * Do you have any idea how to do it differently?
   - Experiments: Which "tricks"/"parts of processing" enhanced the //Attribute recognition// and //Composite activity classification// tasks "the most"? Try to answer why.

====== Answers ======

   - First set
      * list components [[https://docs.google.com/drawings/d/12wIoIDVDV3b6EbJAVVIzZn9h0ymIgHRHi_sTauGM08A/edit|(Google doc graph)]]
      * dependance of components (the same graph)
   - Scripts
      * reason?: Cheap source of training data, Many combinations, unseen variants, “decsriptions” of the same thing
      * four ways: 2x2: 1) direct use of words from data or 2) mapping word classes from WordNet X 3) simple word frequency or 4) TF*IDF
   - There was a discussion about 3rd set of question. We are not sure why authors do that. There was strongly supported opinion that autohors do a lot unnecessary work, which is lost by binarization.
   - 4th: Majority people in aswers nominated the use of TF*IDF in case of no training data as the best idea.