<?xml version="1.0" encoding="utf-8"?>
<feed xmlns="http://www.w3.org/2005/Atom" 
      xmlns:thr="http://purl.org/syndication/thread/1.0">
  <link rel="alternate" type="text/html" href="http://www.readwriteweb.com/archives/hakia_announces_semantic_api.php" />
  <link rel="self" type="application/atom+xml" href="http://www.readwriteweb.com/atom.xml" />
  <id>tag:,2008:/1/tag:www.readwriteweb.com,2008://1.6593-</id>
  <updated>2008-09-24T11:43:45Z</updated>
  <title>Comments for Hakia Announces Semantic API</title>
  
  <generator uri="http://www.sixapart.com/movabletype/">Movable Type 4.1</generator>
  <entry>
    <id>tag:www.readwriteweb.com,2008://1.6593</id>
    <link rel="alternate" type="text/html" href="http://www.readwriteweb.com/archives/hakia_announces_semantic_api.php" />
    <link rel="service.edit" type="application/atom+xml" href="http://www.readwriteweb.com/cgi-bin/mt/mt-atom.cgi/weblog/blog_id=1/entry_id=6593" title="Hakia Announces Semantic API" />
    <published>2008-06-19T19:56:42Z</published>
    <updated>2008-06-19T19:57:53Z</updated>
    <title>Hakia Announces Semantic API</title>
    <summary>Semantic search engine Hakia today announced a set of APIs that opens up their natural language processing and search platform to developers. Hakia&apos;s Syndication Web Services really comes in two parts: search queries, which allow developers to add web search functionality leveraging Hakia&apos;s five billion page index, and XML feed calls, which give developers access...</summary>
    <author>
      <name>Josh Catone</name>
      <uri>http://www.readwriteweb.com/</uri>
    </author>
    
    <category term="Search Services" />
    
    <category term="Semantic Web" />
    
    <content type="html" xml:lang="en" xml:base="http://www.readwriteweb.com/">
      <![CDATA[<p><img border="0" src="http://www.readwriteweb.com/images/hakia-logo.jpg" width="150" height="59" />Semantic search engine <a href="http://www.hakia.com/">Hakia</a> today announced a <a href="http://blog.hakia.com/?p=312">set of APIs</a> that opens up their natural language processing and search platform to developers.  Hakia's Syndication Web Services really comes in two parts: search queries, which allow developers to add web search functionality leveraging Hakia's five billion page index, and XML feed calls, which give developers access to Hakia's underlying natural language processing technology.  The latter of the two is clearly the more compelling of the offerings.</p>]]>
      <![CDATA[<p>Mobile video firm, Berggi, released <a href="http://www.berggisearch.com/">Berggi Search</a>, a mobile search application that lets users search Hakia's index via the API from mobile phones.  Berggi is leveraging the part of the Hakia's API that lets developers lean on the company's search platform -- that, however, is not the part that really interests us.</p>

<p>What is more interesting are the XML feed calls that Hakia is offering that give access to their underlying NLP engine.  Right now, only the "Summarizer" element is available.  Summarizer, which Hakia says can be used to suggest tags or abstracts, analyzes and extracts meaning from large blocks of text or the contents of URLs.  Other elements that are not yet available are Categorizer, which identifies "categorical phrases" in text, Characterizer, which "identifies and expands descriptive keywords or tags," and Text Meaning Representation.</p>

<p>Hakia has an <a href="http://club.hakia.com/syndication.aspx">XML testing form</a> up on their Club Hakia page, and in our testing it seemed a little rough around the edges.  Compared to our testing of <a href="http://www.opencalais.com/">Open Calais</a> from Reuters (<a href="http://www.readwriteweb.com/archives/calais_20_launches.php">our coverage</a>), the summaries and tags the XML testing form returned using the Summarizer element weren't very impressive.  Mostly, it seemed to just return the headline or first sentence as the summary for articles we threw at it.  And for RWW articles, Hakia Summarizer would suggest as tags the tags that we entered by hand in MovableType.</p>

<p>Hakia's Syndication Web Services are free for up to 30,000 requests per day for search services (unlimited free queries for Quotes and Cartoons), and free for up to 1,000 requests per day for XML feed calls.  Have you had a chance to play with Hakia's new semantic API?  If so, what did you think?  How does it compare to Calais or Semantic Hacker? Let us know in the comments below.</p>

<p><i>Full Disclosure: Occasional ReadWriteWeb contributor <a href="http://www.readwriteweb.com/about_emre.php">Emre Sokullu</a> is a technology evangelist at Hakia.</i></p>]]>
    </content>
  </entry>

  <entry>
    <id>tag:www.readwriteweb.com,2008://1.6593-comment:58347</id>
    <thr:in-reply-to ref="tag:www.readwriteweb.com,2008://1.6593" type="text/html" href="http://www.readwriteweb.com/archives/hakia_announces_semantic_api.php"/>
    <link rel="alternate" type="text/html" href="http://www.readwriteweb.com/archives/hakia_announces_semantic_api.php#c58347" />
    <title>Comment from 16 Dollar Beats on 2008-06-19</title>
    <author>
        <name>16 Dollar Beats</name>
        <uri>http://www.16dollarbeats.com</uri>
    </author>
    <content type="html" xml:lang="en" xml:base="http://www.16dollarbeats.com">
        <![CDATA[<p>i JUST READ ABOUT THIS ON ANOTHER WEBSITE. sEEMS LIKE U WOULD GET A BROAD RESULT LIST IF IT PULLS SEARCH TERMS FROM THE TEXT. STILL A GOOD IDEA THOUGH</p>]]>
    </content>
    <published>2008-06-19T20:23:54Z</published>
  </entry>

  <entry>
    <id>tag:www.readwriteweb.com,2008://1.6593-comment:58367</id>
    <thr:in-reply-to ref="tag:www.readwriteweb.com,2008://1.6593" type="text/html" href="http://www.readwriteweb.com/archives/hakia_announces_semantic_api.php"/>
    <link rel="alternate" type="text/html" href="http://www.readwriteweb.com/archives/hakia_announces_semantic_api.php#c58367" />
    <title>Comment from Dominiek on 2008-06-19</title>
    <author>
        <name>Dominiek</name>
        <uri>http://dominiek.com/</uri>
    </author>
    <content type="html" xml:lang="en" xml:base="http://dominiek.com/">
        <![CDATA[<p>Just did a little quick test run on their 'Summarizer'. Unfortunately it doesn't seem to work well with inputting text, sometimes I get a server error and never get any results. The summarize by URL seems to work better. It will return a title and a summary for the page.</p>

<p>It doesn't seem too suitable yet for the use-case of getting a list of keywords/tags related to a piece of content. That is a small use-case I'm trying to accommodate for now.</p>

<p>Will be looking out for their other syndication tools, especially their 'characterizer'.</p>]]>
    </content>
    <published>2008-06-20T03:36:05Z</published>
  </entry>

</feed>