Please enable JavaScript.
Coggle requires JavaScript to display documents.
Natural Language Processing - Coggle Diagram
Natural Language Processing
Introduction
Language and Linguistics
History of NLP
Early 20th Century: The groundwork for NLP was laid by linguists like Ferdinand de Saussure, who proposed that language is a system of signs where meaning is derived from relationships within the language1
1954: The Georgetown experiment demonstrated the first successful use of a machine to translate more than sixty Russian sentences into English. It was predicted that machine translation would be solved within a few years, but progress proved to be slower
1960s: Development of early NLP systems like SHRDLU and ELIZA showed computers could understand simple language in restricted “blocks worlds” or mimic a Rogerian psychotherapist, respectively
1970s: The focus shifted to creating more structured approaches to language understanding, with the development of conceptual ontologies and augmented transition networks (ATNs)
1950s: Alan Turing introduced the concept of a machine’s ability to exhibit intelligent behavior equivalent to, or indistinguishable from, that of a human. This led to the Turing Test, which assesses a machine’s ability to exhibit human-like intelligence, including the use of natural language
1980s: The rise of machine learning algorithms began to replace complex hand-written rules, thanks to increased computational power and a shift away from Chomsky’s transformational grammar towards statistical models
Late 1980s to 1990s: Statistical methods became prevalent, leading to significant improvements in machine translation and other NLP tasks2
21st Century: The introduction of deep learning and neural networks has revolutionized NLP, leading to advancements in language modeling, machine translation, and speech recognition. Today, NLP technologies are integral to various applications, from virtual assistants to sentiment analysis tools
Challenging Areas
Definition of NLP
Interactions between computers and human languages
Computational techniques for text analysis
Goal: Human-like language processing for various applications
Linguistics
Phonetics and Phonology
Morphology
Lexicon
Syntax and Semantics
Common Tasks
Speech Recognition
Part of Speech Tagging
Word Sense Disambiguation
Discourse Analysis
Higher-Level Applications
Machine Translation
Sentiment Analysis
Question Answering
Challenges
Natural Language Understanding
Ambiguity and Contextual Nuances
Common Sense Reasoning
Approaches
Symbolic (Rule-Based)
Statistical
Neural Networks (AI Models)
Future Directions
Semantic Web Integration
Cognitive Computing
Lexicon
Definition: The vocabulary of a language, including words and expressions.
Components: Standard language, non-standard variations, idioms, slang, jargon.
Idioms
Nature: Expressions with meanings not deducible from individual words.
Examples: "Raining cats and dogs", "Spill the beans", "Over the moon".
Usage: Common in everyday speech, literature, and various forms of media.
Non-Standard English
Definition: Variations not conforming to the norms of standard language.
Characteristics: Unique pronunciation, grammar, vocabulary, idioms.
Types: Dialects, sociolects, ethnolects, pidgins, creoles.
N-gram
N-gram is a sequence of N words (or tokens) from a given sample of text.