<?xml version="1.0" encoding="UTF-8"?>
<rss version="2.0"
	xmlns:content="http://purl.org/rss/1.0/modules/content/"
	xmlns:wfw="http://wellformedweb.org/CommentAPI/"
	xmlns:dc="http://purl.org/dc/elements/1.1/"
	xmlns:atom="http://www.w3.org/2005/Atom"
	xmlns:sy="http://purl.org/rss/1.0/modules/syndication/"
	xmlns:slash="http://purl.org/rss/1.0/modules/slash/"
	>

<channel>
	<title>Veeeb &#187; Labs</title>
	<atom:link href="http://veeeb.de/blog/category/labs/feed/" rel="self" type="application/rss+xml" />
	<link>http://veeeb.de/blog</link>
	<description>weblog</description>
	<lastBuildDate>Mon, 05 Nov 2012 07:35:19 +0000</lastBuildDate>
	<language></language>
	<sy:updatePeriod>hourly</sy:updatePeriod>
	<sy:updateFrequency>1</sy:updateFrequency>
	<generator>http://wordpress.org/?v=3.4.2</generator>
		<item>
		<title>entity extraction comparison tool &#8211; opencalais, alchemyAPI, evri</title>
		<link>http://veeeb.de/blog/news/entity-extraction-alchemyapi-evri-opencalais/</link>
		<comments>http://veeeb.de/blog/news/entity-extraction-alchemyapi-evri-opencalais/#comments</comments>
		<pubDate>Mon, 20 Sep 2010 10:57:03 +0000</pubDate>
		<dc:creator>admin</dc:creator>
				<category><![CDATA[Labs]]></category>
		<category><![CDATA[News]]></category>
		<category><![CDATA[alchemyAPI]]></category>
		<category><![CDATA[entity extraction]]></category>
		<category><![CDATA[evri]]></category>
		<category><![CDATA[nlp]]></category>
		<category><![CDATA[opencalais]]></category>
		<category><![CDATA[semantic]]></category>
		<category><![CDATA[veeeb]]></category>

		<guid isPermaLink="false">http://www.veeeb.de/blog/?p=404</guid>
		<description><![CDATA[The veeeb semantic editor currently uses the opencalais API to extract entities from a written text. But opencalais is not the only API out there. In fact there are different entity extraction API&#8217;s and a comparison can be very usefull.  Every API has some features another one doesn&#8217;t. I really liked Rob DiCiucci&#8216;s article about [...]]]></description>
			<content:encoded><![CDATA[<p>The <a title="veeeb homepage" href="http://www.veeeb.com">veeeb semantic editor</a> currently uses the <a title="opencalais" href="http://www.opencalais.com" target="_blank">opencalais API</a> to extract entities from a written text. But opencalais is not the only API out there. In fact there are different entity extraction API&#8217;s and a comparison can be very usefull.  Every API has some features another one doesn&#8217;t.</p>
<p>I really liked <a title="entity extraction content api evaluation" href="http://blog.viewchange.org/2010/05/entity-extraction-content-api-evaluation/" target="_blank">Rob DiCiucci</a>&#8216;s article about the current different semantic services. He covers more than just entity extraction in his article, e.g. the API of <a href="http://www.freebase.com" target="_blank">freebase</a>, which veeeb is using as well or <a title="zemanta" href="http://www.zemanta.com" target="_blank">zemanta</a>, which is more a API for suggesting relevant content directly (interessting, though&#8230;)</p>
<p>Regarding entity extraction the best known free API services right now seem to be</p>
<ul>
<li><a title="alchemyAPI" href="http://www.alchemyAPI.com" target="_blank">http://www.alchemyAPI.com</a></li>
<li><a title="opencalais" href="http://www.opencalais.com" target="_blank">http://www.opencalais.com</a></li>
<li><a title="evri" href="http://www.evri.com" target="_blank">http://www.evri.com</a></li>
</ul>
<p>In order to evaluate the services it is usefull to have the results on one screen directly. Thats why we build an easy <a title="flex" href="http://www.adobe.com/de/products/flex/" target="_blank">Flex </a>GUI where you can just do that.  It provides 2 lists of text &#8211; english and german. Doubleclicking an entry will execute the  semantic services with the text of random news articles I found, but  you can also type or copy&amp;paste your own text.</p>
<p>Try it <a title="entity extraction compare tool" href="http://www.veeeb.com/examples/flex/nlpapicompare/nlpCompare.html" target="_blank">here</a>:</p>
<div id="attachment_408" class="wp-caption alignnone" style="width: 310px"><a href="http://www.veeeb.com/examples/flex/nlpapicompare/nlpCompare.html"><img class="size-medium wp-image-408 " title="nplCompare" src="http://www.veeeb.de/blog/wp-content/uploads/2010/09/nplCompare-300x294.png" alt="entity extraction services comparison" width="300" height="294" /></a><p class="wp-caption-text">entity extraction comparison tool</p></div>
<p><strong>Remark</strong>: opencalais does not work with german text right now. So we have to proxy the requests via <a title="google translate" href="http://translate.google.com" target="_blank">Google Translate</a> to get some results. So do not blame opencalais for disturbing results for german text. But anyway &#8211; it works pretty good <img src='http://veeeb.de/blog/wp-includes/images/smilies/icon_smile.gif' alt=':-)' class='wp-smiley' /> </p>
<p>I will post about the results of our comparison soon.</p>
<p>If you have any suggestions &#8211; let me know.</p>
<p>Happy extracting!</p>
<p>Christoph Diefenthal</p>
<iframe src="http://www.facebook.com/plugins/like.php?href=http%3A%2F%2Fveeeb.de%2Fblog%2Fnews%2Fentity-extraction-alchemyapi-evri-opencalais%2F&amp;layout=button_count&amp;show_faces=true&amp;width=300&amp;height=25&amp;action=like&amp;font=arial&amp;colorscheme=light"  id="fbLikeIframe" name="fbLikeIframe"  scrolling="no" frameborder="0" allowTransparency="true"  class="fbLikeContainer"  style="border:none; overflow:hidden; width:300px; height:25px; display:inline;"  ></iframe>]]></content:encoded>
			<wfw:commentRss>http://veeeb.de/blog/news/entity-extraction-alchemyapi-evri-opencalais/feed/</wfw:commentRss>
		<slash:comments>0</slash:comments>
		</item>
	</channel>
</rss>
