https://wiki.apertium.org/w/index.php?action=history&feed=atom&title=Aragonese_and_Catalan%2FEvaluation 2026-04-04T02:20:20Z Revision history for this page on the wiki MediaWiki 1.34.1 https://wiki.apertium.org/w/index.php?title=Aragonese_and_Catalan/Evaluation&diff=56150&oldid=prev 2016-01-16T08:55:44Z

<p></p> <table class="diff diff-contentalign-left" data-mw="interface"> <col class="diff-marker" /> <col class="diff-content" /> <col class="diff-marker" /> <col class="diff-content" /> <tr class="diff-title" lang="en"> <td colspan="2" style="background-color: #fff; color: #222; text-align: center;">← Older revision</td> <td colspan="2" style="background-color: #fff; color: #222; text-align: center;">Revision as of 08:55, 16 January 2016</td> </tr><tr> <td colspan="2" class="diff-lineno">Line 60:</td> <td colspan="2" class="diff-lineno">Line 60:</td> </tr> <tr> <td class="diff-marker"></td> <td class="diff-context diff-side-deleted"><div>Percentage of unknown words that were free rides: 32.69 %</div></td> <td class="diff-marker"></td> <td class="diff-context diff-side-added"><div>Percentage of unknown words that were free rides: 32.69 %</div></td> </tr> <tr> <td class="diff-marker"></td> <td class="diff-context diff-side-deleted"><div>&lt;/pre&gt;</div></td> <td class="diff-marker"></td> <td class="diff-context diff-side-added"><div>&lt;/pre&gt;</div></td> </tr> <tr> <td colspan="2" class="diff-empty diff-side-deleted"></td> <td class="diff-marker" data-marker="+"></td> <td class="diff-addedline diff-side-added"><br /></td> </tr> <tr> <td colspan="2" class="diff-empty diff-side-deleted"></td> <td class="diff-marker" data-marker="+"></td> <td class="diff-addedline diff-side-added"><div>[[Category:Aragonese and Catalan]]</div></td> </tr> </table>

Juanpabl https://wiki.apertium.org/w/index.php?title=Aragonese_and_Catalan/Evaluation&diff=56149&oldid=prev 2016-01-16T08:54:47Z

<p>Created page with &quot;== Version 0.1 (Beta) == === Naïve coverage === ==== arg-cat ==== &lt;pre&gt; $ cat corpus_narrative.txt | sh corpus-stat-arg-cat.sh Number of tokenised words in the corpus: 37844...&quot;</p> <p><b>New page</b></p><div>== Version 0.1 (Beta) ==<br /> <br /> === Naïve coverage ===<br /> ==== arg-cat ====<br /> &lt;pre&gt;<br /> $ cat corpus_narrative.txt | sh corpus-stat-arg-cat.sh<br /> Number of tokenised words in the corpus: 378440<br /> Number of known words in the corpus: 337924<br /> Coverage: 89.3 %<br /> <br /> $ cat sentencelistanwiki.txt | sh corpus-stat-arg-cat.sh<br /> Number of tokenised words in the corpus: 2673751<br /> Number of known words in the corpus: 2344686<br /> Coverage: 87.7 %<br /> &lt;/pre&gt;<br /> ==== cat-arg ====<br /> &lt;pre&gt;<br /> $ cat ../apertium-es-ca/ca-tagger-data/ca.tagged.txt | sh corpus-stat-cat-arg.sh<br /> Number of tokenised words in the corpus: 24590<br /> Number of known words in the corpus: 22919<br /> Coverage: 93.2 %<br /> <br /> trunk/apertium-eo-ca/tekstaro/ca.crp.txt<br /> $ cat ca.crp.txt | sed &#039;s/^ *[0123456789]*\.//g&#039;| sh ./corpus-stat-cat-arg.sh<br /> Number of tokenised words in the corpus: 567608<br /> Number of known words in the corpus: 497165<br /> Coverage: 87.6 %<br /> &lt;/pre&gt;<br /> === Translation Quality ===<br /> ==== cat-arg ====<br /> &lt;pre&gt;<br /> $../apertium-eval-translator/apertium-eval-translator.pl -test MT.txt -ref postedit.txt<br /> Test file: &#039;MT.txt&#039;<br /> Reference file &#039;postedit.txt&#039;<br /> <br /> Statistics about input files<br /> -------------------------------------------------------<br /> Number of words in reference: 1311<br /> Number of words in test: 1315<br /> Number of unknown words (marked with a star) in test: 156<br /> Percentage of unknown words: 11.86 %<br /> <br /> Results when removing unknown-word marks (stars)<br /> -------------------------------------------------------<br /> Edit distance: 203<br /> Word error rate (WER): 15.48 %<br /> Number of position-independent correct words: 1132<br /> Position-independent word error rate (PER): 13.96 %<br /> <br /> Results when unknown-word marks (stars) are not removed<br /> -------------------------------------------------------<br /> Edit distance: 254<br /> Word Error Rate (WER): 19.37 %<br /> Number of position-independent correct words: 1081<br /> Position-independent word error rate (PER): 17.85 %<br /> <br /> Statistics about the translation of unknown words<br /> -------------------------------------------------------<br /> Number of unknown words which were free rides: 51<br /> Percentage of unknown words that were free rides: 32.69 %<br /> &lt;/pre&gt;</div>

Juanpabl