[ 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:automatic-domain-adaptation-for-parsing1 [2011/09/14 18:31]
ramasamy
courses:rg:automatic-domain-adaptation-for-parsing1 [2011/09/14 18:50] (current)
ramasamy
Line 2: Line 2:
 Comments by : Loganathan Comments by : Loganathan
  
-==== Objective ====+===== Objective ====
 +The objective of the paper is to make the statistical parsers adapting to new domains. Best parsing model for a particular testing data is identified by combining training data(source mixture) from different domains. This source mixture is learned from a regression model which will identify the appropriate parsing model. 
  
 ===== Comments ===== ===== Comments =====
Line 9: Line 10:
    * Training and testing were reported in the development set not on the parsing models.    * Training and testing were reported in the development set not on the parsing models.
    * It was noted that the parser has been tested across various domains.    * It was noted that the parser has been tested across various domains.
-   Entroy feature was not clear. +   Entropy feature was not clear.  
 +   * The idea was to successfully adapt to new domains than to achieve very good accuracy for a particular domain
  
-==== What do we like about the paper: ====+===== What do we like about the paper: =====
    * The multiple source adaptation method can identify the factors which affect the parsing accuracy for texts from different domains.    * The multiple source adaptation method can identify the factors which affect the parsing accuracy for texts from different domains.
    * They successfully included methods for domain detection compared to previous works.    * They successfully included methods for domain detection compared to previous works.
 +   * Inclusion of self trained corpora helped avoiding data sparsity in small corporas.
  
-==== What do we dislike about the paper: ==== +===== What do we dislike about the paper: ===== 
-   *   +   *  Results (just before section 7) could have been better explained. 
-  +
- +
- +
- +
  

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