<?xml version="1.0" encoding="UTF-8"?>
<feed xml:lang="en-US" xmlns="http://www.w3.org/2005/Atom">
  <title>Nick Sieger: RubyConf: Natural language generation and processing in Ruby</title>
  <id>tag:blog.nicksieger.com,2005:Typo</id>
  <generator uri="http://www.typosphere.org" version="4.0">Typo</generator>
  <link rel="self" type="application/atom+xml" href="http://blog.nicksieger.com/xml/atom10/article/92/feed.xml"/>
  <link rel="alternate" type="text/html" href="http://blog.nicksieger.com/articles/2006/10/22/rubyconf-natural-language-generation-and-processing-in-ruby"/>
  <updated>2007-08-31T17:44:20+00:00</updated>
  <entry>
    <author>
      <name>george_naing@yahoo.com</name>
    </author>
    <id>urn:uuid:9b113fd0-e6d6-486c-b625-859308cf7ddc</id>
    <published>2006-12-10T10:24:19+00:00</published>
    <updated>2007-08-31T17:44:20+00:00</updated>
    <title>Comment on RubyConf: Natural language generation and processing in Ruby by george_naing@yahoo.com</title>
    <link rel="alternate" type="text/html" href="http://blog.nicksieger.com/articles/2006/10/22/rubyconf-natural-language-generation-and-processing-in-ruby#comment-168"/>
    <content type="html">&lt;p&gt;Can you please suggest resources, docs etc for segmenting a text into senetences? I would prefer a Ruby implementation, thanks a lot in advance.&lt;/p&gt;</content>
  </entry>
  <entry>
    <author>
      <name>Nick Sieger</name>
    </author>
    <id>urn:uuid:f68bccbd-4e2e-4029-9a3a-a2128a39d8f3</id>
    <published>2006-10-22T00:07:34+00:00</published>
    <updated>2007-08-31T16:57:20+00:00</updated>
    <title>RubyConf: Natural language generation and processing in Ruby</title>
    <link rel="alternate" type="text/html" href="http://blog.nicksieger.com/articles/2006/10/22/rubyconf-natural-language-generation-and-processing-in-ruby"/>
    <category term="rubyconf" scheme="http://blog.nicksieger.com/articles/tag/rubyconf"/>
    <category term="rubyconf2006" scheme="http://blog.nicksieger.com/articles/tag/rubyconf2006"/>
    <content type="html">&lt;p&gt;&lt;em&gt;Speaker: Michael Granger&lt;/em&gt;&lt;/p&gt;

&lt;p&gt;Michael&amp;#8217;s talk was full of excellend pre-recorded video demos, and thus was difficult to note-take.  Instead, here are links to most of the pieces of software he discussed for your perusal:&lt;/p&gt;

&lt;ul&gt;
&lt;li&gt;&lt;a href="http://gemjack.com/gems/stemmer-1.0.1/classes/Stemmable.html"&gt;Stemmable&lt;/a&gt; &amp;#8211; implementation of Porter stemming algorithm&lt;/li&gt;
&lt;li&gt;rubyreuters &amp;#8211; text categorizer using Reuters corpus&lt;/li&gt;
&lt;li&gt;&lt;a href="http://chronic.rubyforge.org/"&gt;Chronic&lt;/a&gt; &amp;#8211; natural language date-time parser in pure Ruby&lt;/li&gt;
&lt;li&gt;&lt;a href="http://www.deveiate.org/code/Ruby-WordNet.html"&gt;Ruby-WordNet&lt;/a&gt; &amp;#8211; ruby interface to &lt;a href="http://wordnet.princeton.edu/"&gt;WordNet&lt;/a&gt; lexical dictionary&lt;/li&gt;
&lt;li&gt;&lt;a href="http://www.advogato.org/proj/Ruby-LinkParser/"&gt;Ruby-LinkParser&lt;/a&gt; &amp;#8211; binding to the &lt;a href="http://www.link.cs.cmu.edu/link/"&gt;Link Grammar&lt;/a&gt; library (from Carnegie Mellon)&lt;/li&gt;
&lt;li&gt;&lt;a href="http://www.nict.go.jp/jt/a132/members/mutiyama/software.html"&gt;Sentence alignment and concordance tools&lt;/a&gt; by UTIYAMA Masao&lt;/li&gt;
&lt;li&gt;&lt;a href="http://www.deveiate.org/projects/Linguistics/wiki/English"&gt;Ruby-Linguistics&lt;/a&gt; &amp;#8211; framework for linguistic utilities for Ruby objects in any language, by Michael, sports WordNet and LinkParser integration&lt;/li&gt;
&lt;/ul&gt;</content>
  </entry>
</feed>
