GROUP 8 – NATURAL LANGUAGE PROCESSING HISTORY OF NATURAL LANGUAGE PROCESSING

 Ferdinand De Saussure
NATURAL LANGUAGE PROCESSING
In the early 1900s, a Swiss linguistics professor named
Natural language processing (NLP) refers to the branch Ferdinand de Saussure died, and in the process, almost
of computer science—and more specifically, the branch deprived the world of the concept of “Language as a
of artificial intelligence or AI—concerned with giving Science.” From 1906 to 1911, he offered three courses
computers the ability to understand text and spoken at the University of Geneva, where he developed an
words in much the same way human beings can. approach describing languages as “systems
NLP combines computational linguistics—rule-based  Albert Sechehaye & Charles Bally
modeling of human language—with statistical, machine
learning, and deep learning models. Together, these Two of his colleagues, Albert Sechehaye and Charles
technologies enable computers to process human Bally, recognized the importance of his concepts. From
language in the form of text or voice data and to these, they wrote the Cours de Linguistique Générale,
‘understand’ it’s full meaning, complete with the published in 1916.
speaker or writer’s intent and sentiment.
 Alan Turing
In 1950, Alan Turing wrote a paper describing a test for
NLP TASKS a “thinking” machine. In 1952, the Hodgkin-Huxley
model showed how the brain uses neurons in forming
 Speech recognition, also called speech-to-text, an electrical network.
is the task of reliably converting voice data into
 Noam Chomsky
text data. Speech recognition is required for any
application that follows voice commands or Noam Chomsky published Syntactic Structures in 1957.
answers spoken questions. With this as his goal, Chomsky created a style of
 Part of speech tagging, also called grammatical grammar called Phase-Structure Grammar, which
tagging, is the process of determining the part methodically translated natural language sentences into
of speech of a particular word or piece of text a format that is usable by computers.
based on its use and context.
 Word sense disambiguation is the selection of
the meaning of a word with multiple meanings  Return of Natural Language Processing
through a process of semantic analysis that
determines the word that makes the most sense  Year 1980’s – 1990’s
in the given context.
 Named entity recognition, or NEM, identifies The AI stoppage had initiated a new phase of fresh
words or phrases as useful entities. NEM ideas, with earlier concepts of machine translation
identifies ‘Kentucky’ as a location or ‘Fred’ as a being abandoned, and new ideas promoting new
man's name. research, including expert systems. Until the 1980s, the
 Named entity recognition, or NEM, identifies majority of NLP systems used complex, “handwritten”
words or phrases as useful entities. NEM rules. In 1997, LSTM recurrent neural net (RNN) models
identifies ‘Kentucky’ as a location or ‘Fred’ as a were introduced and found their niche in 2007 for voice
man's name. and text processing.
 Sentiment analysis attempts to extract
 After the Year 2000
subjective qualities, attitudes, emotions,
sarcasm, confusion, suspicion—from text. In 2001, Yoshio Bengio and his team proposed the first
 Natural language generation is sometimes neural “language” model, using a feed-forward neural
described as the opposite of speech recognition network. In this type of network, the data moves only in
or speech-to-text; it's the task of putting one direction, from input nodes, through any hidden
structured information into human language. nodes, and then on to the output nodes.

DELGADO FETALSANA GALICIA GREGORIO HISTORILLO SALIBIO

  Year 2011 APPLICATIONS AND EXAMPLES OF NLP
Apple’s Siri became known as one of the world’s first  Autocomplete in Search Engines
successful NLP/AI assistants. Siri’s automated speech
recognition module translates the owner’s words into Autocomplete suggestions and be taken to results
digitally interpreted concepts. without having to manually type every character.
 Language Translation
TYPES OF NATURAL LANGUAGE PROCESSING The process of converting the written word from one
language into another language.
 Machine learning (ML)
Examples :( Google Translate, I Translate)
A field of study in artificial intelligence concerned with
 Smart assistants
the development and study of statistical algorithms that
can effectively generalize and thus perform tasks It is a virtual assistant which is software that is installed
without explicit instructions. on mobile devices that helps in answering questions,
tasks, or services.
 Machine Translation
Examples: (Amazon's Alexa, Siri)
Is use of either rule-based or probabilistic machine
learning approaches to translation of text or speech  Predictive Text
from one language to another, including the contextual,
idiomatic and pragmatic nuances of both languages. It is an input technology that facilitates typing on a
device by suggesting words. Examples: (SwiftKey,
 Named- entity Recognition Gboard (Google Keyboard)
Also known as ' entity identification, entity chunking,  Automatic Summarization
and entity extraction) is a subtask of information
extraction that seeks to locate and classify named The process of shortening a set of data computationally.
entities mentioned in unstructured text. Examples: (Quillboot, Automatic Video Summarization)

 Document classification  Sentiment Analysis

Is a problem in library science, information science and Process of analyzing digital text to determine if the
computer science. The task is to assign a document to emotional tone of the message is positive, negative, or
one or more classes or categories. neutral. Examples: (Talkwalker, Brand24)

 Part- Of- Speech Tagging  Chatbot

In corpus linguistics, part-of-speech tagging, also called A computer program designed to simulate conversation
grammatical tagging is the process of marking up a word with human users, especially over the internet.
in a text (corpus) as corresponding to a particular part of Examples: (Google's Bard, Cici)
speech.
 Natural language generation
It is concerned with the construction of computer
systems that can produce understandable texts in
English or other human languages from some
underlying non-linguistic representation of information.

DELGADO FETALSANA GALICIA GREGORIO HISTORILLO SALIBIO

 7 Benefits of Natural Language Processing
(NLP)
HOW CAN NATURAL LANGUAGE PROCESSING CHANGE
 Improved Communication AND IMPROVE OUR WAY OF LIVING?

NLP enables machines to understand and respond to Natural Language Processing (NLP) has the potential to
human language, enhancing communication between change the way we live by improving communication
humans and computers. between humans and machines. One of the significant
effects of NLP can be seen in virtual assistants like Siri
 Language Translation and Alexa, which rely on language understanding to
carry out commands and provide information. In
NLP plays a crucial role in language translation, breaking healthcare, NLP facilitates better analysis of medical
down language barriers and facilitating global records, aiding diagnosis and treatment planning.
communication. Additionally, in customer service, NLP-powered chatbots
 Sentiment Analysis allow businesses to provide instant and personalized
responses to user inquiries. Translation services also
NLP can be used to analyze sentiments expressed in benefit from NLP, breaking down language barriers and
texts, helping businesses gauge public opinion, fostering global communication. As NLP continues to
customer feedback, and brand perception. advance, its applications in various sectors, from
education to finance, hold the promise of streamlining
processes and improving overall efficiency, ultimately
 Search Engine Optimization (SEO) improving our quality of life.
NLP contributes to better search engine results by
understanding user queries and delivering more
accurate and relevant information.
 Healthcare Applications
In healthcare, NLP assists in extracting information from
medical records, aiding in diagnosis, research, and
improving overall patient care.
 Personalized User Experiences
By understanding user preferences and behaviors
through language, NLP enables the creation of
personalized experiences in applications, websites, and
services.
 Accessibility
NLP contributes to making technology more accessible
by enabling voice-controlled interfaces and assisting
individuals with disabilities.

DELGADO FETALSANA GALICIA GREGORIO HISTORILLO SALIBIO