Lecture 1. Introduction

Lecture 1. Introduction

Brief history of NLP

• January 7, 1954 — Georgetown experiment. Russian to English machine translation;
• 1957 — Noam Chomsky introduced "universal grammar";
• since 1961 — Brown Corpus;
• the late 1960's — ELIZA, a simulation of a psychotherapist;
• 1975 — Vector Space Model by Salton;
• up to the early 1980's — rule based approaches;
• after the early 1980's — machine learning, corpus linguistics;
• 1998 — Language Model by Ponte and Croft;
• since 1999 — topic modeling (LSI, pLSI, LDA, etc);
• 1999 — "Foundations of Statistical Natural Language Processing" by Manning and Shuetze;
• 2009 — "Natural Language Processing with Python" by Bird, Klein, and Loper.

Major tasks of NLP

• Machine Translation
• Text classification
  • Sentiment analysis
  • Spam filtering
  • Classification by topic or by genre
• Text clustering
• Named entity recognition
• Question answering
• Automatic summarization
• Natural language generation
• Speech recognition
• Spell checking
• User study design and evaluation