Yliopiston etusivulle In English
Helsingin yliopisto
clt231: Introduction to Natural Language Processing - lukuvuosi 2009-2010

Yhteystiedot

Nykykielten laitos

PL 24 (Unioninkatu 40)
00014 HELSINGIN YLIOPISTO

Puhelin +358 (09) 1911 (vaihde)
Faksi +358 (09) 191 28313

1. Getting Started with NLTK.

  • Lecture notes
  • Further reading
  • Practical work
    • Open Python IDLE from the Start menu and do:
      >>> import nltk
      >>> from nltk.book import *
      
    • Searching Text
      Choose an English word, and see how it is used in the different example texts by making concordances. Try other words. Find a word that is used frequently in one text and never used in the other texts.
    • Generating Text
      Generate paragraphs in the style of each different example text, using generate(). An example is shown in Searching Text.
    • Spoken Dialog Systems
      What is the TuringTest? Have a conversation with at least two different NLTK chatbots. Do any of these chatbots pass the test?
    • IDLE
      Learn more about IDLE with One Day of IDLE Toying by Danny Yoo.
  • NLTK demos (optional)
    • In IDLE, run this NLTK application:
      >>> nltk.app.rdparser()
      
    • Keep clicking Step for a while and try to see what's going on. Alternatively, click Autostep once and just watch.
    • Challenge: can you parse the whole sentence successfully using only the Expand, Match and Backtrack buttons?
    • In IDLE, run this NLTK application:
      >>> nltk.app.srparser()
      
    • Keep clicking Step for a while and try to see what's going on.
    • Challenge: can you parse the whole sentence successfully using only the Shift and Reduce buttons?
© 2006-2009 Graham Wilcock

Hae laitoksen sivuilta:

Laitoksen etusivulle | Tiedekunnan etusivulle | Yliopiston etusivulle

Copyright © 2003-2005 Helsingin yliopisto. Kaikki oikeudet pidätetään.