fnielsen · September 21, 2014 22:50
diff --git a/string_for_tokenization.py b/string_for_tokenization.py
 s = u"""DTU course 02819 is taught by Mr. Finn Årup Nielsen,
 Ph.D. Some of aspects of the course are: machine learning and web
 2.0. The telephone to Finn is (+45) 4525 3921, and his email is
 [email protected]. A book published by O'Reilly called 'Programming
 Collective Intelligence' might be useful. It costs $39.99 or 285.00
 kroner in Polyteknisk Boghandle. Is 'Text Processing in Python'
 appropriate for the course? Perhaps! The constructor function in
 Python is called "__init__()". fMRI will not be a topic of the
 course."""
	s = u"""DTU course 02819 is taught by Mr. Finn Årup Nielsen,
	Ph.D. Some of aspects of the course are: machine learning and web
	2.0. The telephone to Finn is (+45) 4525 3921, and his email is
	[email protected]. A book published by O'Reilly called 'Programming
	Collective Intelligence' might be useful. It costs $39.99 or 285.00
	kroner in Polyteknisk Boghandle. Is 'Text Processing in Python'
	appropriate for the course? Perhaps! The constructor function in
	Python is called "__init__()". fMRI will not be a topic of the
	course."""