https://wiki.apertium.org/w/index.php?action=history&feed=atom&title=User%3AFpetkovski%2FGSOC_2012_ReportUser:Fpetkovski/GSOC 2012 Report - Revision history2026-06-20T14:29:52ZRevision history for this page on the wikiMediaWiki 1.34.1https://wiki.apertium.org/w/index.php?title=User:Fpetkovski/GSOC_2012_Report&diff=52687&oldid=prevUnhammer: backlink2015-02-09T11:18:45Z<p>backlink</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 11:18, 9 February 2015</td>
</tr><tr>
<td colspan="2" class="diff-lineno">Line 2:</td>
<td colspan="2" class="diff-lineno">Line 2:</td>
</tr>
<tr>
<td class="diff-marker"></td>
<td class="diff-context diff-side-deleted"><div>* [[Corpus based preposition selection - HOWTO]]</div></td>
<td class="diff-marker"></td>
<td class="diff-context diff-side-added"><div>* [[Corpus based preposition selection - HOWTO]]</div></td>
</tr>
<tr>
<td class="diff-marker"></td>
<td class="diff-context diff-side-deleted"><div>* [[Building a pseudo-parallel corpus]]</div></td>
<td class="diff-marker"></td>
<td class="diff-context diff-side-added"><div>* [[Building a pseudo-parallel corpus]]</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"><div>* [[Ideas for Google Summer of Code/Corpus-based lexicalised feature transfer]]</div></td>
</tr>
<tr>
<td class="diff-marker"></td>
<td class="diff-context diff-side-deleted"><br /></td>
<td class="diff-marker"></td>
<td class="diff-context diff-side-added"><br /></td>
</tr>
<tr>
<td class="diff-marker"></td>
<td class="diff-context diff-side-deleted"><div>==Reports==</div></td>
<td class="diff-marker"></td>
<td class="diff-context diff-side-added"><div>==Reports==</div></td>
</tr>
</table>Unhammerhttps://wiki.apertium.org/w/index.php?title=User:Fpetkovski/GSOC_2012_Report&diff=40286&oldid=prevFrancis Tyers: moved GSOC 2012 Report to User:Fpetkovski/GSOC 2012 Report2013-04-11T13:16:05Z<p>moved <a href="/w/index.php?title=GSOC_2012_Report&action=edit&redlink=1" class="new" title="GSOC 2012 Report (page does not exist)">GSOC 2012 Report</a> to <a href="/wiki/User:Fpetkovski/GSOC_2012_Report" title="User:Fpetkovski/GSOC 2012 Report">User:Fpetkovski/GSOC 2012 Report</a></p>
<table class="diff diff-contentalign-left" data-mw="interface">
<tr class="diff-title" lang="en">
<td colspan="1" style="background-color: #fff; color: #222; text-align: center;">← Older revision</td>
<td colspan="1" style="background-color: #fff; color: #222; text-align: center;">Revision as of 13:16, 11 April 2013</td>
</tr><tr><td colspan="2" class="diff-notice" lang="en"><div class="mw-diff-empty">(No difference)</div>
</td></tr></table>Francis Tyershttps://wiki.apertium.org/w/index.php?title=User:Fpetkovski/GSOC_2012_Report&diff=40269&oldid=prevFpetkovski: Created page with '==Documentation / HOWTO== * Corpus based preposition selection - HOWTO * Building a pseudo-parallel corpus ==Reports== * Lexical feature transfer - First report * […'2013-04-11T12:19:24Z<p>Created page with '==Documentation / HOWTO== * <a href="/wiki/Corpus_based_preposition_selection_-_HOWTO" title="Corpus based preposition selection - HOWTO">Corpus based preposition selection - HOWTO</a> * <a href="/wiki/Building_a_pseudo-parallel_corpus" title="Building a pseudo-parallel corpus">Building a pseudo-parallel corpus</a> ==Reports== * <a href="/wiki/Lexical_feature_transfer_-_First_report" title="Lexical feature transfer - First report">Lexical feature transfer - First report</a> * […'</p>
<p><b>New page</b></p><div>==Documentation / HOWTO==<br />
* [[Corpus based preposition selection - HOWTO]]<br />
* [[Building a pseudo-parallel corpus]]<br />
<br />
==Reports==<br />
* [[Lexical feature transfer - First report]]<br />
<br />
* [[Lexical feature transfer - Second report]]<br />
<br />
==TODO==<br />
<br />
* '''Try generating corpus from monolingual SL corpus:'''<br />
** Оваа лабавост на регулативите се одразува врз третманот на уапсените корисници на дрога.<br />
<s>*** Run through lexical transfer <code>mk-en-biltrans</code><br />
*** Run through <code>apertium-lex-tools/scripts/biltrans-to-multitrans.py</code><br />
*** Run through the rest of the pipeline from <code>apertium-transfer -b</code> onwards<br />
*** Run through <code>apertium-lex-learner/irstlm-ranker</code></s><br />
** This will give:<br />
<s>*** SL:TL selection possibilities <br />
*** probabilities from the TL language model for each selection</s><br />
** Select a subset for training where one translation has a substantially higher proportion of the probability mass than the rest.<br />
** Look at finding out how to work out what "substantially" should be.<br />
<br />
* '''Improve current method:'''<br />
<s>** Split test corpus in two (dev, test)<br />
*** Rerun the experiments and check with test corpus<br />
*** Look at dev corpus to see what kind of patterns there are in lines that aren't getting matched<br />
** Look at combining the 1-feature with the 2-feature model as backoff.<br />
</s><br />
* '''Evaluation'''<br />
** Try pair bootstrap resampling between best system and default translation for both WER and BLEU.<br />
<br />
* ''' Check the bidix entries that were added automatically'''<br />
<br />
[[Category:Users|Fpetkovski]]</div>Fpetkovski