Open WolfgangFahl opened 3 years ago
This is partly a Natural Language Processing (NLP)/ Named Entity Recognition (NER) task. See https://stackoverflow.com/questions/tagged/geograpy for some library options
select count(locality) from event_wikicfp where locality is not null 73214 select count(distinct(locality)) from event_wikicfp 15673
10 most common examples from wikicfp, followed by 5 rare examples with different spelling and some more rare examples
count locality 1372 Singapore 749 Beijing, China 704 Paris, France 649 Barcelona, Spain 625 Rome, Italy 616 Hong Kong 575 Bangkok, Thailand 502 Vienna, Austria 497 Athens, Greece ... 3 Montreal, QC, CANADA 3 Montreal, Quebec, Canada 3 Montréal, Québec, Canada 3 Moscow, Russian Federation 3 Moscow,Russia ... 1 Aachen (Germany) 1 Aachen / Germany 1 Aachen, Germany 1 Aachen,Germany
This is partly a Natural Language Processing (NLP)/ Named Entity Recognition (NER) task. See https://stackoverflow.com/questions/tagged/geograpy for some library options
10 most common examples from wikicfp, followed by 5 rare examples with different spelling and some more rare examples