Please enable JavaScript.
Coggle requires JavaScript to display documents.
Natural Language Processing (Challanges (phonology, morphology, lexicon,…
Natural Language Processing
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.
Language
Formal
Syntax
generative grammar, co-ref resolution, parsing, auto-summary, xml, relationship extraction
Semantics
The possible meanings of a sentence by focusing on the interactions among word-level meanings in the sentence
Natural
Requirements
Linguistics
Phonetics
Phonology
speech recognition, part-of-speech tagging
Morphology
segmentation, morphemes and words
Lexicon
dictionary, word sense disambiguation (5), named entity recognition
focuses on formal, structural models of language and the discovery of language universals
Computer Science
Cognitive Psychology
History
1950s
1950s Turing “computer machinery and intelligence” test
1954 Georgetown experiment - auto translation from Russian to English
1960s
1960s Eliza - (Weizenbaum) psychotherapist
1970s
Conceptual ontologies - the nature of being
1980s
complex hand-written (programmed) rules, then machine learning algorithms used
Challanges
phonology
morphology
lexicon
syntax
semantics
discourse analysis
pragmatics
optical character recognition
Machine Learning
Advantages
auto-focus on most common cases
use stats to deal with unfamiliar input
improves with more data, not more programming
Machine learning is an application of artificial intelligence (AI) that provides systems the ability to automatically learn and improve from experience without being explicitly programmed