MetaCarta is Where It’s At

Filed under: Alternative GIS, Data Processing and Conversion, Geotagging — geoLibro @ 4:06 am

MetaCarta’s GeoTagger apparently does excellent, impressive, cool work on unstructured documents. The result of its awesomeness is geotagged xml with which one can do whatever one pleases. Make sense? I spoke to a sales rep from MetaCarta at the Indianapolis “What’s New with ArcGIS 9.2” seminar about GeoTagger and grilled him about what could be done. Not too many specifics from that, but then I got a call from the great MetaCarta themselves since I expressed interest. Unless they’re mean-spirited liars, GeoTagger does do natural language processing and does put out very useful xml and does handle versioned data and does include user-specified structured data (think MySQL tables) and does…do more still.

But today’s post is a leech off of Fantom Planet’s post about another slick product built on top of GeoTagger. It’s PageMapper, and you can think of it as a more invasive, more thorough GeoTagThings. Sounds like it’s a little lab-y still, but have you built such a system?



  1. I am interested in getting more details regarding

    “GeoTagger does do natural language processing”


    Comment by Antonio Valderrábanos — 2006.October.26 @ 8:20 am

  2. Antonio, I should preface this by saying I have no inside knowledge or even practical knowledge of how well GeoTagger works. From what I’m told, its natural language processing uses pretty advanced algorithms that can identify places and contextualize them. So a document that references Dingo, Oklahoma can be interpreted differently than a wiki entry about a dingo. How they actually do this is surely beyond my understanding. They claim to be able to process relative geography as well, so “18 miles east of the Notre Dame campus” gets placed, well, 18 miles east of the Notre Dame campus. How hey handle the myriad decisions involved in even that one statement I don’t know (where is the Notre Dame campus? 18 miles straight east?)

    They extract temporal references as well, but I imagine they’re a lot less intellligent about these. There is a little literature at ( and I don’t know if their specific project or its underlying technology has been written about in the professional literature. Someday soon I’ll want to find out, though, because it’s very compelling and very promising and I already want it.

    Comment by geoLibro — 2006.October.26 @ 11:52 am

  3. Many thanks, Cris. What you sketch is enough to give an idea of what they are doing. Besides, the link is also helpful.


    Comment by Antonio Valderrábanos — 2006.October.26 @ 3:00 pm

  4. I’m certain you could ring them up and start a discussion. They’re very approachable folks.

    Comment by gwhiz — 2006.November.29 @ 4:29 am

  5. I spoke to one of their reps at an Indianapolis ESRI event and got the feeling they believe they’re sitting on something very big. Anyway, one of their account manager types called me a few days later and indeed he was very personable and had a lot to say about the Tagger in particular. Didn’t know the tech stuff, but he did say that it wasn’t prohibitively expensive to license it and put it to work on local collections. Of course, you say “not prohibitively expensive,” I say “never in a million years” and call the whole thing off.

    Comment by geoLibro — 2006.November.29 @ 1:32 pm

RSS feed for comments on this post. TrackBack URI

Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s

Blog at

%d bloggers like this: