Milestone

Metrics (Marc, Cynthia) :

• Kullback-Leibler(Marc)
  • Wikipedia : http://en.wikipedia.org/wiki/Kullback%E2%80%93Leibler_divergence
  • Done but with weird results
• Chi-square (Cynthia)

Topics (Farah, Jeremy):

- Create an unique id to the article.

- Link every 1 gram to its own article and year

- Shape matrix Article X 1-gram

Language coverage (Malik, Gil):

- Coverage of language by the top k% most used words.

- Frequency of a given n-gram over years.

- Frequency of unique n-grams over years

Synonyms (Tao, Nicolas):

- load the list of synonyms + needed n-grams in a SQL database

- Build web interface to display plots with frequency evolution over time