[T1] Research that shows being aware of certain linguistic phenomena
and designing a statistical system accordingly improves performance.
[T2] New methods in incorporating linguistic knowledge into
statistical systems to improve the start of the art.
(e.g., as rules in a preprocessing step, as linguistic features in
a statistical system, as filters for pruning a search space, as priors
in an objective function).
[T3] Research that demonstrates the feasibility of creating NLP systems to
automatically acquire linguistic knowledge for a large number of
languages.
[T4] Research that demonstrates the benefits of using NLP techniques to
help some particular linguistic studies. For instance, given some
language data, which language family should a particular language
belong to? How do languages interact with each other? How do
language evolve over the time? What are the main differences between
two dialects of the same languages (e.g., British English and American
English)?