Ivan’s private site

November 14, 2008

Calais Release 4 and the Linking Data cloud…

Just got to this news via Yves’s blog: Reuters’ Open Calais service comes with a new release in January, and this will bind to the Linked Data cloud. To quote the official blog of Reuters:

Release 4 of Calais will be a big deal. In that release we’ll go beyond the ability to extract semantic data from your content. We will link that extracted semantic data to datasets from dozens of other information sources, from Wikipedia to Freebase to the CIA World Fact Book. In short – instead of being limited to the contents of the document you’re processing, you’ll be able to develop solutions that leverage a large and rapidly growing information asset: the Linked Data Cloud.

Ie: when analyzing a text, Open Calais will return URIs into DBPedia, Freebase, Musicbrainz… Thereby opening up the possibility for various of applications that would not be possible (or would be fairly complicated) without. One more step to make it possible to reuse all those data on the Web… Yey!

B.t.w.: I write these lines using WordPress and I have Zemanta’s Firefox plugin running to generate the tags. However, as far as I know (I may be wrong!), the Zemanta service does not provide those URI-s yet (they do provide some URI-s in their return format, but I am not sure those are LOD URIs). Maybe some day?

(Thanks to Yves for drawing my attention on this…)

(Note after the original publication of the blog: it seems I was wrong and Zemanta does have a similar feature, see Andraz’ comment.)



  1. Hi Ivan,

    Yes, Zemanta already provides Freebase GUIDs and Wikipeida URLs. So both Freebase and DBPedia can already be linked by using Zemanta API.

    People are already using it that way – for example Faviki.com (semantic tagging site) is using Zemanta to suggest semantic tags (=dbpedia entities), so users don’t need to type them in themselves. They even use dbpedia’s cross language links to suggest semantic tags in native languages.

    You can check out the API via http://developer.zemanta.com

    (Freebase RDF URLs are coming next week, since this is just a syntactical change from GUIDs)

    Andraz Tori, Zemanta

    Comment by Andraz Tori — November 14, 2008 @ 18:02

  2. Ah! My bad! I am actually a user of Faviki, but it was not clear to me that not only tags but also, say, dbpedia uris are returned by Zemanta. I also looked at the Zemanta developer’s site, but I did not find this information. It is obviously my mistake…

    Comment by Ivan Herman — November 14, 2008 @ 18:36

  3. Hi Herman,

    yes, today Zemanta’s API officially stopped flying low on the radar and was released to wider public.

    It does support RDF output, links to Linking Open Data entities and has properly defined namespace:


    Comment by Andraz Tori — December 9, 2008 @ 13:22

RSS feed for comments on this post.

Blog at WordPress.com.

%d bloggers like this: