Place Name Disambiguation

May 27, 2006

One of the most interesting parts of the 'natural language geocoder' is Place Name Disambiguation. Depending on the context, the grammatical structure or the language a term may have one of several possible meanings. Examples :

  • Hayden : the CIA director Michael Hayden or the city in Idaho.
  • Java : the island or the programming language
  • Brisbane : city in Australia or city in California, USA
  • Como : city in Italy or a very frequent word in Spanish.

We are using several processing steps to tackle this problem. First we identify the language of the text and the contexts (Example : In an IT context the term java most likely stands for the programming language).

Then we try to find person names and we do some simple grammatical analysis using coocurrences of left and right neighbours (Example : If the term we are looking at is preceded by the expression 'south of', we can be nearly certain that the term has a geographical meaning.)

About these ads

2 Responses to “Place Name Disambiguation”


  1. [...] Many words have several meanings e.g. Java, so an important part is Place Name Disambiguation. The RSS-to-GeoRSS-Converter checks the grammatical structure plus the context and detects the most interesting word as place or toponym, which may be for example a city, a volcano, a building or a country. All is done within seconds. [...]


  2. [...] What’s going on is that the RSS feed from this blog is being converted to GeoRSS by the Geonames service Geonames examines the feed to see if it can pick out any place names. Should a place be identified, Geonames looks up the latitude and longiotude, then encodes this into the RSS feed. It’s obviously not perfect, a post about Jack London for example would locate the gnarly author in Oxford Street rather than the Klondike, though clever disambiguation technology helps Geonames make an intelligent guess at the context of the place name. Explore Our Pla.net is helping to improve the natural language geocoder with a feature that lets you pass feedback to the geonames server. [...]


Leave a Reply

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

WordPress.com Logo

You are commenting using your WordPress.com 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

Follow

Get every new post delivered to your Inbox.

Join 37 other followers

%d bloggers like this: