[ Skip to the content ]

Institute of Formal and Applied Linguistics Wiki

[ Back to the navigation ]

You are here: start » courses » rg » 2012 » encouraging-consistent-translation

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
Next revision Both sides next revision
courses:rg:2012:encouraging-consistent-translation [2012/10/17 11:44]
dusek 		courses:rg:2012:encouraging-consistent-translation [2012/10/17 11:59]
dusek
Line 57: Line 57:
     * but rules are very similar, so we also need something less fine-grained     * but rules are very similar, so we also need something less fine-grained
   * C2 is a target-side feature, just counts the target side tokens (only the "most important" ones; in terms of TF-IDF)   * C2 is a target-side feature, just counts the target side tokens (only the "most important" ones; in terms of TF-IDF)
-    * It may be compared to Language Model features, but is trained only on the target part of the bilingual training data.+    * It may be compared to Language Model features, but is trained only on the target part of the bilingual tuning data.
   * C3 counts occurrences of source-target token pairs (and uses the "most important" term pair for each rule, again)   * C3 counts occurrences of source-target token pairs (and uses the "most important" term pair for each rule, again)
  
Line 63: Line 63:
   * They need two passes through the data   * They need two passes through the data
   * You need to have document segmentation   * You need to have document segmentation
-    * Since the frequencies are trained on the training set, you can just translate one document at a time, no need to have full sets of documents+    * Since the frequencies are trained on the tuning set (see Sec. 5), you can just translate one document at a time, no need to have full sets of documents 
 + 
 +==== Sec. 5. Evaluation and Discussion ==== 
 +**Choice of baseline** 
 +  * Baselines are quite nice and competitive, we believe this really is an improvement 
 +  * MIRA is very cutting-edge 
 + 
 +**Tuning the feature weights** 
 +  * For the 1st phase, "heuristically" probably means they just used some reasonable enough values, e.g. from earlier experiments 
 +    * This is in order to speed up the experiment, they don't want to wait for MIRA twice. 
 + 
 +**Different evaluation metrics** 
 +  * The BLEU variants do not differ that much, only in Brevity Penalty for multiple references 
 +    * IBM BLEU uses the reference that is closest to the MT output (in terms of length), NIST BLEU uses the shortest one 
 +  * This was probably just due to some technical reasons, e.g. they had their optimization software designed for one metric and not the other 

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