Natural

Language
Processing
Topics Covered
01 What is NLP
Think for a moment how we listen and talk: how are brain processes
language. Now imagine how computers need to do that? For this,
Natural Language Processing is used.

02 History of NLP
Think about how this was made! Therefore it is important for us to go
through the history of this language.

03 Uses
In today’s world NLP is used in various scenarios. From the
technology present around us to many more.

04 Advantage & Disadvantage

If something is created for a purpose, then their can be some
advantage and disadvantage about it. In this slide, we will go through
some of them.
What is NLP?
 Natural language processing (NLP) is a subfield of linguistics, computer
science, and artificial intelligence concerned with the interactions between
computers and human language, in particular how to program computers to
process and analyze large amounts of natural language data.

 The goal is a computer capable of "understanding" the contents of documents,

including the contextual nuances of the language within them. The technology
can then accurately extract information and insights contained in the
documents as well as categorize and organize the documents themselves.

 Challenges in natural language processing frequently involve speech

recognition, natural-language understanding, and natural-language generation.
 Natural language processing (NLP) is a subfield of linguistics, computer science, and
artificial intelligence concerned with the interactions between computers and human
language, in particular how to program computers to process and analyze large
amounts of natural language data. The goal is a computer capable of "understanding"
the contents of documents, including the contextual nuances of the language within
them.

The technology can then accurately extract information and insights contained in the
documents as well as categorize and organize the documents themselves.
Challenges in natural language processing frequently involve speech recognition,
natural-language understanding, and natural-language generation.
History of NLP
 History of NLP

1950s
The Georgetown experiment in 1954 involved fully automatic
translation of more than sixty Russian sentences into English. The
authors claimed that within three or five years, machine
translation would be a solved problem.
Little further research in machine translation was conducted until
the late 1980s when the first statistical machine translation
systems were developed.

1960s
Some notably successful natural language processing systems
developed in the 1960s were SHRDLU, a natural language system
working in restricted "blocks worlds" with restricted vocabularies,
and ELIZA, a simulation of a Rogerian psychotherapist, written by
Joseph Weizenbaum between 1964 and 1966.
 History of NLP

1970s
During the 1970s, many programmers began to write "conceptual ontologies", which structured real-
world information into computer-understandable data. Examples are MARGIE (Schank, 1975), SAM
(Cullingford, 1978), PAM (Wilensky, 1978), TaleSpin (Meehan, 1976), QUALM (Lehnert, 1977),
Politics (Carbonell, 1979), and Plot Units (Lehnert 1981). During this time, the first chatterbots were
written (e.g., PARRY). B ri e
fing
1980s
The 1980s and early 1990s mark the heyday of symbolic methods in NLP.
An important development (that eventually led to the statistical turn in the 1990s) was the
rising importance of quantitative evaluation in this period.
 History of NLP

1990s
Many of the notable early successes on statistical methods in NLP occurred in the field of
machine translation, due especially to work at IBM Research. These systems were able to take
advantage of existing multilingual textual corpora that had been produced by the Parliament of
Canada and the European Union.
As a result, a great deal of research has gone into methods of more effectively learning from
limited amounts of data.

2000s
With the growth of the web, increasing amounts of raw (unannotated) language data has
become available since the mid-1990s. Research has thus increasingly focused on unsupervised
and semi-supervised learning algorithms.
Generally, this task is much more difficult than supervised learning, and typically produces less
accurate results for a given amount of input data
 History of NLP

2010s
In the 2010s, representation learning and deep neural network-style machine learning methods became
widespread in natural language processing.
This is increasingly important in medicine and healthcare, where NLP helps analyze notes and text in
electronic health records that would otherwise be inaccessible for study when seeking to improve care.
Briefi
ng
Uses of NLP
 Voice Assistants
I am sure you’re all used to Siri, Alexa, or Google Assistant. All these voice
assistants use speech recognition, natural language understanding, and processing to
understand the verbal commands of the user and perform actions accordingly. From
the time they were introduced to now, they have transformed into a very reliable
gadget.

Market Intelligence
Marketers can use natural language processing to understand their customers in a
better way and use those insights in creating effective strategies. The power of NLP
equips them for analyzing topics, keywords, and making proper use of unstructured
data. It can also be used to identify customers’ pain points and keep an eye on your
competitors.
 Sentiment Analysis
Humans have the gift of being sarcastic and ironic during conversations. With
sentiment analysis in real time, you can monitor the mentions on social media and
tackle them before they escalate. This application of NLP gives your company the
power to sense the pulse of the customers. It also equips you to gauge the customer’s
reaction to your latest digital marketing campaign. Sentiment analysis can be done by
companies on a periodic basis to understand the deeper aspects of the business.

Text Summarization
This NLP application is used to summarize text by extracting the most important
information. The main goal here is to reduce the process of going through vast amounts of
data in news content, legal documentation and scientific papers. There are 2 ways of using
natural language processing for text summarization: extraction based, which extracts key
phrases and creates a summary without adding any extra information AND abstraction
based summarization, which paraphrases the original content to create new phrases.
 Email Filters
NLP makes use of a technique called text classification to filter emails. It refers to
the process of classification of a piece of text into predefined categories. Examples of
this include getting an incoming mail classified into primary, promotions, and social
sections and also the classification of articles into different categories so that you can
choose to read the material of your choice.

Chatbots
They are a form of artificial intelligence that are programmed to interact with humans in
such a way that they sound like humans themselves. Depending on the complexity of the
chatbots, they can either just respond to specific keywords or they can even hold full
conversations that make it tough to distinguish them from humans. Chatbots are created
using Natural Language Processing and Machine Learning, which means that they
understand the complexities of the English language and find the actual meaning of the
sentence and they also learn from their conversations with humans and become better
with time.
Advantage & Disadvantage
Advantages
 NLP system offers exact answers to the questions, no unnecessary or unwanted some information. The
accuracy of the answer increases with the amount of relevant information provided in the questions.

 Structuring a high unstructured data source. Users can ask questions about any subject and get a direct
response in seconds. It is easy to implement. Using a program is less costly than hiring a person. A person
can take two or three times longer than a machine to execute the tasks mentioned.

 NLP system provides answers to the questions in natural language. Allow you to perform more language-
based data compares to a human being without fatigue and in an unbiased and consistent way.

 NLP process help computer communicate with a human in their language and scales other language-
related tasks. It is a faster customer service response time
Disadvantages
 Can’t differentiate similar phrases If there’s one major disadvantage with NLP, it’s the challenges it faces with
differentiation among similar words. By similar expressions, we mean words that sound the same but have
different meanings. For example: ‘I scream and ice cream,’ ‘I ran to the grocery shop because I ran out of food,’
and more expressions.

 Sarcasm Some humor and sarcasm can be funny, but machine learning models aren’t evolved enough to process
this. Even though many people may have seen jokes made with voice technology apps such as Siri, Cortana,
machine models will always process things positively or negatively.

 Speech errors Miss-spelled words or misused one can create a range of issues when analyzing text. Unfortunately,
even though grammar apps and auto-correct can handle these types of mistakes, they can’t ever understand the
writer’s intentions. Different dialects and mispronunciations can challenge the machine to understand what you
are trying to say.

 Lack of research NLP has come a long way for most commonly used, particularly in the most common languages.
However, many parts of the world still haven’t provided enough data for NLP to analyze. For example, Africa is
considered one of the poorest continents in the world but has more than 2000 languages worldwide. However,
there isn’t enough data from each of these African languages. In North Africa, the most widely spoken language is
Arabic, but in Central and the more southern parts, each district will have a different language. There are even
countries in Africa that have several languages.
  One of the most essential Natural
NLTK with ML and DL Language Processing (NLP) tools for
solving many types of problems is the
NLTK library.

 The natural language toolkit (NLTK)

offers numerous utility for solving a
multitude of Natural Language
Processing problems. The NLTK library
is very well suited for linguistic-based
tasks.

 It offers a wide range of options for

tasks such as classification,
tokenization, stemming, tagging,
parsing, and semantic reasoning.

 There is so much you can do with this

library and then use the methods of the
bag of words, Term frequency-inverse
document frequency (TF-IDF), word to
vectors, and other similar methods to
approach these tasks and problems.
 Conclusion
Natural Language Processing is one of the best
subjects and sub-topics to learn in Artificial
Intelligence. There are so many research papers and
articles that are being published continuously. Rapid
developments and extensive research are consistently
taking place on a daily basis. In the upcoming years,
a lot more amazing discoveries to be made in the
following field.