Difference between revisions of "Evaluation"

From Apertium
Jump to navigation Jump to search
(those links are so hard to hit)
Line 1: Line 1:
  +
{{TOCD}}
New section coming soon!
 
   
 
==Using apertium-eval-translator for WER and PER==
 
==Using apertium-eval-translator for WER and PER==
Line 41: Line 41:
 
==Evaluating with Wikipedia==
 
==Evaluating with Wikipedia==
 
{{main|Evaluating with Wikipedia}}
 
{{main|Evaluating with Wikipedia}}
  +
  +
==See also==
  +
* [[Regression testing]]
   
 
[[Category:Evaluation]]
 
[[Category:Evaluation]]

Revision as of 12:37, 7 June 2010

Using apertium-eval-translator for WER and PER

apertium-eval-translator is a script written in Perl. It calculates the word error rate (WER) and the position-independent word error rate (PER) between a translation performed by an Apertium-based MT system and its human-corrected translation at document level. Although it has been designed to evaluate Apertium-based systems, it can be easily adapted to evaluate other MT systems.

Usage

    apertium-eval-translator -test testfile -ref reffile [-beam <n>]

    Options:

      -test|-t     Specify the file with the translation to evaluate 
      -ref|-r      Specify the file with the reference translation 
      -beam|-b     Perform a beam search by looking only to the <n> previous 
                   and <n> posterior neigboring words (optional parameter 
                   to make the evaluation much faster)
      -help|-h     Show this help message
      -version|-v  Show version information and exit

    Note: The <n> value provided with -beam is language-pair dependent. The
    closer the languages involved are, the lesser <n> can be without
    affecting the evaluation results. This parameter only affects the WER
    evaluation.

    Note: Reference translation MUST have no unknown-word marks, even if
    they are free rides.

    This software calculates (at document level) the word error rate (WER)
    and the postion-independent word error rate (PER) between a translation
    performed by the Apertium MT system and a reference translation obtained
    by post-editing the system ouput.

    It is assumed that unknow words are marked with a start (*), as Apertium
    does; nevertheless, it can be easily adapted to evaluate other MT
    systems that do not mark unknown words with a star.

See English and Esperanto/Evaluation for an example. In Northern Sámi and Norwegian there is a Makefile to translate a set of source-language files and then run the evaluation on them.

Evaluating with Wikipedia

Main article: Evaluating with Wikipedia

See also