Hi Sands,
as far as I know there is no strategy for extracting entity types for
elements in Wikipedia lists articles.
In my opinion it would be interesting to develop such an idea.
Main tasks would be:
- correctly identify lists articles (only based on article title?)
- extract elements from lists articles (all the wikilinks in the list
articles?)
- mapping of list context to a DBpedia type. That is possibly the hardest
part. Should NLP be used?
Maybe this could become a GSoC project.
Do you have any approach to propose?
BTW, looks like the Hydrogen article is using Infobox_hydrogen which is not
in the DBpedia mappings, hence no type is extracted for that entity.
Cheers
Andrea
Il 28/gen/2014 20:27 "Sands Alden Fish" <sa...@mit.edu> ha scritto:
> Hi All,
>
> Is there currently a strategy in place for explicitly linking entities
> referred to in a Wikipedia list? For example, I just went looking for a
> quick way to visualize one image representation of each element, but the
> data came up short. This list exists, but only has metadata about the list
> itself:
>
> http://dbpedia.org/page/List_of_elements
>
> and when navigating to a specific element:
>
> http://dbpedia.org/page/Hydrogen
>
> there is only a type "Thing" specified. In the absence of an explicit
> entity type, having a list that actually enumerated its items would be
> extremely useful, and of course there are a *lot* of lists on Wikipedia.
>
> Am I missing a structure here, or does it not exist yet?
>
>
> Cheers,
>
> - Sands Fish
> - Data Scientist / Software Engineer
> - MIT Libraries
> - sa...@mit.edu
> - E25-131
>
>
>
> ------------------------------------------------------------------------------
> WatchGuard Dimension instantly turns raw network data into actionable
> security intelligence. It gives you real-time visual feedback on key
> security issues and trends. Skip the complicated setup - simply import
> a virtual appliance and go from zero to informed in seconds.
>
> http://pubads.g.doubleclick.net/gampad/clk?id=123612991&iu=/4140/ostg.clktrk
> _______________________________________________
> Dbpedia-discussion mailing list
> Dbpedia-discussion@lists.sourceforge.net
> https://lists.sourceforge.net/lists/listinfo/dbpedia-discussion
>
>
------------------------------------------------------------------------------
WatchGuard Dimension instantly turns raw network data into actionable
security intelligence. It gives you real-time visual feedback on key
security issues and trends. Skip the complicated setup - simply import
a virtual appliance and go from zero to informed in seconds.
http://pubads.g.doubleclick.net/gampad/clk?id=123612991&iu=/4140/ostg.clktrk
_______________________________________________
Dbpedia-discussion mailing list
Dbpedia-discussion@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/dbpedia-discussion
