|
What is the best method to make location disambiguation for geonames data? There are some scoring algorithm for geonames search, but they do not open source it and I'm not sure it very sophisticated. (i.e. for soma, ca it returns Soma lake in Canada which haven't even wikipedia article, instead of very popular Soma Neirbohood in san francisco) There also some works I have found in google scholar, but they seems very shallow and similar with my heuristics like scoring by something(log(population) + 1000hasWikipedia(article)+ isCity100+isCapital(10)). My domain in travel articles som my scoring function should provide most probable tourist places(cities, place of interest(Disneyland, colleseum, big ben)). Do you know any important articles describing geocoding algorithms used in production by Google maps, yahoo, bing? |
|
This will sound like a plug for my own work but I think a book chapter we wrote on Entity Linking might give you a good summary of existing approaches to this problem, for all kinds of entities (not just geonames), and describes a state-of-the-art supervised learning system for doing this task. In particular, you should look at the features section for what works for places. Thanks, great article.
(Mar 14 '12 at 03:42)
yura
|
