<html><head><style type="text/css"><!-- DIV {margin:0px;} --></style></head><body><div style="font-family:times new roman,new york,times,serif;font-size:12pt"><div>
<meta http-equiv="CONTENT-TYPE" content="text/html; charset=utf-8">
<title></title>
<meta name="GENERATOR" content="OpenOffice.org 3.1 (Linux)">
<style type="text/css">
<!--
@page { margin: 0.79in }
P { margin-bottom: 0.08in }
A:link { so-language: zxx }
-->
</style>
<p style="margin-bottom: 0in;">Dear Members</p>
<p style="margin-bottom: 0in;"><br>
</p>
<p style="margin-bottom: 0in;">I am going to use MICA parser as a
dependency parser in an XTAG based Machine Translation system. The
main reason for doing this work is the low speed of the XTAG parser
available in “<a href="ftp://ftp.cis.upenn.edu/pub/xtag/lem/">ftp://ftp.cis.upenn.edu/pub/xtag/lem/</a>”.
</p>
<p style="margin-bottom: 0in;">Unlike the XTAG parser, MICA can find
the derivation trees set very fast. But, its loading time is an
obstacle in using it. I am looking for a solution to load it once and
use it as a server for many times. It seems that the major problem is
related to the time when it is running a “MaxEntDecoder”. Would
you please guide me how can I solve this problem?</p>
<p style="margin-bottom: 0in;"><br>
</p>
<p style="margin-bottom: 0in;">Regards,</p>
<p style="margin-bottom: 0in;">Basirat</p>
</div>
</div></body></html>