<span style="color:rgb(0,0,0)">Hi Mohammad,</span><br style="color:rgb(0,0,0)"><br style="color:rgb(0,0,0)"><span style="color:rgb(0,0,0)">MaltOptimizer
also gathers information about some properties, such as the percentage
of non-projective arcs/trees which is by the way crucial in order to
select the best parsing algorithm. And indeed it optimizes the
feature model. Finally it tunes the parameters of the learning algorithm
and creates an option file and a feature specification file.</span><br style="color:rgb(0,0,0)">
<br style="color:rgb(0,0,0)"><span style="color:rgb(0,0,0)">About
the learning time, it depends on the size of the training corpora. Of
course if the system comes up with a very complex feature model or
suggests a slower parsing algorithm (some Malt algorithms require more
time than others) it affects the learning time. Nevertheless, the system
guarantees that the suggested configuration is the best in performance
that it can find. <br>By the way, the time differences with the same training
corpus are not very wide.</span><br style="color:rgb(0,0,0)">
<br style="color:rgb(0,0,0)"><span style="color:rgb(0,0,0)">I recommend you to visit the website (</span><a style="color:rgb(0,0,0)" href="http://nil.fdi.ucm.es/maltoptimizer" target="_blank">http://nil.fdi.ucm.es/maltoptimizer</a><span style="color:rgb(0,0,0)">) and if you are at all interested in MaltOptimizer or you have any further
questions (or need help) do not hesitate to contact me directly.</span><br style="color:rgb(0,0,0)">
<br style="color:rgb(0,0,0)"><span style="color:rgb(0,0,0)">Best,</span><br style="color:rgb(0,0,0)"><span style="color:rgb(0,0,0)">Miguel.</span><br><br><div class="gmail_quote">On 17 February 2012 15:29, Mohammad Sadegh Rasooli <span dir="ltr"><<a href="mailto:rasooli.ms@gmail.com">rasooli.ms@gmail.com</a>></span> wrote:<br>
<blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><div dir="ltr">Hello Miguel,<br>Do you mean that the mentioned tool works as a combined feature selection and learner model parameter selection tool? How this optimization affects learning speed?<br>
Thanks<br><br>Mohammad Sadegh Rasooli<br>
Head of the Persian Dependency Treebank Project: <a href="http://dadegan.ir/en/persiandependencytreebank" target="_blank">http://dadegan.ir/en/persiandependencytreebank</a><br><br><div class="gmail_quote"><div><div class="h5">
On Fri, Feb 17, 2012 at 5:30 PM, Miguel Ballesteros <span dir="ltr"><<a href="mailto:miguelballesteros1@gmail.com" target="_blank">miguelballesteros1@gmail.com</a>></span> wrote:<br>
</div></div><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><div><div class="h5"><div>Let us introduce MaltOptimizer, an optimization tool for MaltParser.<br><br>MaltOptimizer has been (and is) developed by <a href="http://nil.fdi.ucm.es/index.php?q=node/449" target="_blank">Miguel Ballesteros</a> from <a href="http://www.ucm.es/" target="_blank">Complutense University of Madrid</a> (Spain) and <a href="http://stp.lingfil.uu.se/%7Enivre/" target="_blank">Joakim Nivre</a> from <a href="http://www.uu.se/en/" target="_blank">Uppsala University</a> (Sweden).<br>
<br>Freely
available statistical parsers often require careful optimization to
produce state-of-the-art results, which can be a non-trivial task
especially for application developers who are not interested in parsing
research for its own sake. MaltOptimizer is a freely available tool
developed to facilitate parser optimization with the open-source system
MaltParser, which offers a wide range of parameters for optimization,
including nine different parsing algorithms, two different machine
learning libraries (each with a number of different learners), and an
expressive specification language that can be used to define arbitrarily
rich feature models. MaltOptimizer is an interactive system that first
performs an analysis of the training set in order to select a suitable
starting point for optimization and then guides the user through the
optimization of parsing algorithm, feature model, and learning algorithm
parameters. <br> <br>The system will be demonstrated in the System Demonstration Session at <a href="http://eacl2012.org/home/index.html" target="_blank">EACL 2012</a> and is further described in a paper to appear at <a href="http://www.lrec-conf.org/lrec2012/" target="_blank">LREC 2012</a>. </div>
<br>For further information and download: <a href="http://nil.fdi.ucm.es/maltoptimizer" target="_blank">http://nil.fdi.ucm.es/maltoptimizer</a><br><br>Best regards,<br>Miguel and Joakim<span style="color:rgb(153,153,153)"></span><br>
<br></div></div>_______________________________________________<br>
UNSUBSCRIBE from this page: <a href="http://mailman.uib.no/options/corpora" target="_blank">http://mailman.uib.no/options/corpora</a><br>
Corpora mailing list<br>
<a href="mailto:Corpora@uib.no" target="_blank">Corpora@uib.no</a><br>
<a href="http://mailman.uib.no/listinfo/corpora" target="_blank">http://mailman.uib.no/listinfo/corpora</a><br>
<br></blockquote></div><br></div>
</blockquote></div><br><br clear="all"><br>-- <br><span style="color:rgb(153,153,153)">Miguel Ballesteros </span><br><font color="#888888">Universidad Complutense de Madrid<br>NIL, Natural Interaction based on Language<br>
<a href="http://nil.fdi.ucm.es/index.php?q=node/449" target="_blank">Website</a></font><br><br><br>