[ 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
external:addicter [2011/05/22 09:27]
mphi
external:addicter [2011/05/22 09:31] (current)
mphi
Line 7: Line 7:
 ==== TODOs ==== ==== TODOs ====
   * test alignment with synonym detection (cz_wn required) = separating ''lex::'' and ''disam::''   * test alignment with synonym detection (cz_wn required) = separating ''lex::'' and ''disam::''
 +  * try misplaced phrase detection
 +    * parse the reference, extrapolate unto the hypothesis via word alignment, get phrases from there
 +    * group adjacent words aligned to the same word? (imitation)
   * order evaluation   * order evaluation
-    * a lot of background research 
     * currently finds misplaced items, but their shift distances are off     * currently finds misplaced items, but their shift distances are off
 +    * not important for ''ows'' vs ''owl'', but
       * to fix -- for every misplaced token       * to fix -- for every misplaced token
         * if it (and only it) were to be moved in the original permutation, what would be the best place?         * if it (and only it) were to be moved in the original permutation, what would be the best place?
         * evaluate with nr. of intersections         * evaluate with nr. of intersections
-  * try domain adaptation for word alignmentEMNLP 2011 paper +  * try domain adaptation for word alignment with the "via source" alignment (EMNLP 2011 paper) 
-  * comb and comment the code +  * technical 
-  * add help files +    * comb and comment the code 
-  * integrate with the rest of Addicter+    * add help files 
 +    * integrate with the rest of Addicter
   * approach applicable to learner's corpora   * approach applicable to learner's corpora
     * see Anne Lüdelig, TLT9     * see Anne Lüdelig, TLT9
-  * adapt Addicter to Sara's program+  * try Blast (Sara's program for translation error markup)
   * alternative to reference-based evaluation: "Inconsistencies in Penn parsing", M. Dickinson   * alternative to reference-based evaluation: "Inconsistencies in Penn parsing", M. Dickinson
  

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