Foundations of Statistical Natural Language Processing

Christopher D. Manning and Hinrich Schütze

Chapter 1: Introduction

Links referred to in the text

• The Brown corpus is available from ICAME (a tagged version of the Brown corpus is also available with the Penn Treebank)
• The Lancaster-Oslo-Bergen corpus is available from ICAME
• Susanne corpus
• The Penn Treebank project (LDC Catalog entry)
• Canadian Hansards: searchable interface for 1986-93 and LDC catalog entry.
• WordNet
• Tom Sawyer: local copy or available from and prepared by The University of Virginia Electronic Text Center, the Oxford Text Archive, and Project Gutenberg (perhaps try the Sailor's Project Gutenberg site mirror).

Teaching materials

• Acrobat slides for figures and tables in section 1.4 Dirty Hands

Other links

• Wentian Li on Zipf's Law
• The Hansards (British Columbia)
• Java interfaces to WordNet:
  • JWNL (jdidion)
  • Dan Bikel's
  • JWordNet