[ Skip to the content ]

Institute of Formal and Applied Linguistics Wiki


[ Back to the navigation ]

Differences

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

Link to this comparison view

Both sides previous revision Previous revision
Next revision
Previous revision
courses:rg:2014:mdsm [2014/11/29 02:02]
nguyenti
courses:rg:2014:mdsm [2014/11/29 13:52] (current)
popel
Line 1: Line 1:
-You should focus on the first paper (skip section 2.3) +You should focus on the first paper (you can skip section 2.3): [[http://www.aclweb.org/anthology/W11-2503.pdf|Distributional semantics from text and images]]. 
-The second paper, an extent of the first one, is optional reading.+The second paper [[http://www.aclweb.org/anthology/P12-1015.pdf|Distributional Semantics in Technicolor]], an extent of the first one, is optional reading.
  
  
 Q1.  Q1. 
-a)Recall the paper about word representations presented by Tam on November 10.+Recall the paper about word representations presented by Tam on November 10.
 Read http://www.quora.com/Whats-the-difference-between-distributed-and-distributional-semantic-representations Read http://www.quora.com/Whats-the-difference-between-distributed-and-distributional-semantic-representations
  
Line 10: Line 10:
 What does w, d and k mean? What does w, d and k mean?
 What are the values of w, d and k used in the experiments in this paper? What are the values of w, d and k used in the experiments in this paper?
- 
-b) What is maximum dimension of a word vector in distributional representation approach? 
  
 Q2. Q2.
Line 24: Line 22:
          
 b) How do they deal with high dimension of vectors in those papers? b) How do they deal with high dimension of vectors in those papers?
-Can you suggest some other techniques to manage vector dimension?+Can you suggest some (othertechniques of preprocessing vectors with high dimensions?
            
 Q3.  Q3. 
 a) What are Bag of Word (BOVW) and Bag of Visual Word (BOW)? a) What are Bag of Word (BOVW) and Bag of Visual Word (BOW)?
-b) How do they apply BOVW to compute representation of a word (concept) from a large set of Images?+b) How do they apply BOVW to compute representation of a word (concept) from a large set of images?
        
-Q4.+Q4 (bonus).
 When they construct text-based vectors of words from DM model When they construct text-based vectors of words from DM model
 they mentioned Local Mutual Information score. (section 3.2, also section 2.1 in the 2nd paper) they mentioned Local Mutual Information score. (section 3.2, also section 2.1 in the 2nd paper)
 So what is that score? Why did they use it? So what is that score? Why did they use it?
  
-Q5:+Q5 (bonus).
 Have you ever wished to see beautiful "Mermaids"? Have you ever wished to see beautiful "Mermaids"?
 Have you ever seen "Unicorns" in the real life? Have you ever seen "Unicorns" in the real life?

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