NLP Notes

From Adam Colton
Jump to navigation Jump to search

Lectures

Basic Text Processing

Regular Expressions

A formal language for specifying text strings. We will be using [[1]]

  • Disjunctions - square brackets or pipe
  • Negation - ^ right after bracket
  • ? - previous character is optional
  • * 0 or more
  • + 1 or more
  • . any single character
  • ^begin of line
  • $end of line
  • \ for escaping

False Postiives - Type I errors and False Negatives Type II errors.

Regular Expressions in Practical NLP

Word Tokenization

Word Normalization and Stemming

Sentence Segmentation

Retrieved from "https://wiki.adamcolton.net/index.php?title=NLP_Notes&oldid=2390"