Please enable JavaScript.
Coggle requires JavaScript to display documents.
NATURAL LANGUAGE PROCESSING - Coggle Diagram
NATURAL LANGUAGE PROCESSING
Language
- main means of communication between two people.
Natural language
A customary system of spoken, written, or manually signed symbols that people use to represent themselves as members of a social group and participants in its culture.
Human language
Formal language
Formal language in computer science is made up of letters, symbols, and tokens that are derived from the alphabet and are produced in accordance with a predetermined set of rules.
Java
C
Python
NLP
Interactions between computers and human languages.
A set of computational techniques for analyzing and representing naturally occurring texts (at one or more levels) for the purpose of achieving human-like language processing for a range of applications.
To be concerned in NLP
Linguistics:
focuses on formal, structural models of language and the discovery of language universals – the field of NLP was originally referred to as Computational Linguistics.
Computer Science:
concerned with developing internal representations of data and efficient processing of these structures.
Cognitive Psychology:
looks at language usage as a window into human cognitive processes, and has the goal of modeling the use of language in a psychologically plausible way.
Phonetics
How people make and perceive sounds, or the corresponding features of sign in the context of sign language.
Phonology
Interpretation of speech sounds within and across words.
Sound might give a big hint about the meaning of a word or a sentence - tonal languages.
Morphology
Understanding distinct words according to their morphemes (smallest units of meanings)
Lexicon
Understanding everything about distinct words according to their position in the speech, their meanings and their relation to other words.
Syntax
Analyzing the words of a sentence to uncover the grammatical structure.
Semantics
The possible meanings of a sentence by focusing on the interactions among word-level meanings in the sentence.
Discourse Analysis
Properties of the text as a whole that convey meaning by making connections between component sentences
Pragmatics
Explains how extra meaning is read into texts without actually being encoded in them.
History
Until 1980s - complex hand-written (programmed) rules, then machine learning algorithms used
1960s Eliza - (Weizenbaum) psychotherapist
Restricted vocabulary set
Works in “blocks world”
1970s Conceptual ontologies - the nature of being
Programs structure real-world information into computer-understandable data.
Example - chatterbots = Jabberwacky (1997), ALICE.
1954 Georgetown experiment - auto translation from Russian to English.
1950s Turing “computer machinery and intelligence” test
Machine learning
The science of teaching computers to behave without explicit programming is known as machine learning.
Advantages
Use stats to deal with unfamiliar input.
Improves with more data, not more programming
Auto-focus on most common cases.
Applications
Clever searches
N-gram character model
N letter sequences
Markov chain probability - next depends only on preceding
Prediction on corpus of text
Can be trained
N - gram character model
Good progress
Word sense disambiguation - different meanings, same word.
Parsing - grammatical analysis of sentence - ambiguous
Coreference resolution - match pronouns with referring expressions
IE - Google calendar
Sarcasm
Genre classification
Big Data
Machine translation
Sentiment analysis - identify trends in public opinion
Really hard
Topic segmentation and recognition
Word segmentation
Dialogue
NL generation
Summarize
NL understanding
Paraphrase
Sentence breaking
Question Answering
Mostly solved
NER
Language identification
OCR
Spelling correction
POS
World Knowledge
Knowledge integration with NLP systems.
Ontologies and graphs of knowledge.
Common sense logic.
Replicate human thinking
Reason with knowledge that is true by default
Reason rapidly across a broad range of domains
Tolerate uncertainty in your knowledge
Web links
https://simplicable.com/new/natural-language-vs-formal-language#google_vignette
https://www.techtarget.com/searchenterpriseai/definition/natural-language-processing-NLP#:~:text=Natural%20language%20processing%20(NLP)%20is,in%20the%20field%20of%20linguistics
.
https://www.stillmantranslations.com/language-functions-of-language-definition-of-language-translations/
https://arts-sciences.buffalo.edu/linguistics/about/what-is-linguistics.html