Differences

This shows you the differences between two versions of the page.

--- courses:rg:2013:composite-activities [2013/04/23 04:31]
machys vytvořeno
+++ courses:rg:2013:composite-activities [2013/09/29 21:35] (current)
machys
@@ Line 1: / Line 1: @@
-   - After reading first three chapters:
+   - After reading the first three chapters:
-      * list the main parts/components/stuctures of the model.
+      * list the main parts/components/structures of the model.
-      * How is their creation dependant on each other?
+      * Is their creation dependent on other components?
-   - Thinking about the scripts (recipes):
+   - Thinking about the scripts:
-      * What is the main reason (the biggest advantage) of using scripts? What kind of information it brings? (Hint: page 2, page 8)
+      * What is the main reason (the biggest advantage) of using scripts? What kind of information does it bring? (Hint: page 2, page 8)
-      * Truth is - authors don't get the "knowledge" of scripts straightforward - how is that "knowledge" represented in model and which (two) ways are used to get it.
+      * 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 last paragraph of section 3 theres described method that enhances the robustness of the model (binarization of all association weights <html> <math xmlns="http://www.w3.org/1998/Math/MathML" alttext="association weights"> <msubsup><mi>w</mi><mi>i</mi><mo>z</mo></msubsup> </math> </html>). Answer one of following questions (choose one):
+   - 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 it works? (=> Why it should work the best?)
+      * Why does it work? (=> Why should it work best?)
-      * Have you any idea how to make it different way.
+      * Do you have any idea how to do it differently?
-   - In experiements part, which tools enhanced the tasks Atribute recognition and Composite activity classification "the most". Why?
+   - 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.

[ Back to the navigation ] [ Back to the content ]

Institute of Formal and Applied Linguistics Wiki

Differences