<HTML><HEAD>
<META charset=UTF-8 http-equiv=Content-Type content="text/html; charset=utf-8">
<META content="MSHTML 6.00.2800.1141" name=GENERATOR></HEAD>
<BODY style="FONT-SIZE: 10pt; FONT-FAMILY: Arial; BACKGROUND-COLOR: #ffffff">
<DIV>
<DIV>In a message dated 1/14/2004 5:50:17 AM Pacific Standard Time, lars@aronsson.se writes:</DIV>
<BLOCKQUOTE style="PADDING-LEFT: 5px; MARGIN-LEFT: 5px; BORDER-LEFT: blue 2px solid"><FONT face=Arial>Is there any freely available open source software for spell checking<BR>(or natural language parsing) that handles multiword expressions? I<BR>want an algorithm that can approve "nota bene", "ad notam" and "San<BR>Francisco" (if these MWEs are in the dictionary) in an English text<BR>without approving the member words on their own.</FONT></BLOCKQUOTE></DIV>
<DIV>There is a HyperLaw application currently under development which includes alternatives that may be of interest to you. It is not yet ready for publication.</DIV>
<DIV> </DIV>
<DIV>Gerard Peregrin</DIV></BODY></HTML>