NLP- NATURAL LANGUAGE PROCESS

In this Paper, we are going to take a look at a very interesting research field called Natural Language
Processing. To understand this concept, we need to go back into long past history where humans
communicate without any voices through Cave paintings. They could express thoughts and feelings by
means of signs or gestures. The need for communicating in a form less limited by time and space led to
drawings or markings on objects of any solid material. These messages lasted as long as the materials
themselves. If the pictures were intended to record an event or to convey a message, they were a form of
writing.

However, they somehow manage to communicate and share information, our ancestors were unable to
control their vocalization at the time when gestures were used to communicate, however, as they slowly
began to control their voices and sounds, spoken language began to evolve, now that’s where the
concept of developing a language comes in. As the time passes new languages were produced by human
beings, we speak around 6500 languages around the globe till date.

Back to square one, language is just a means of communication between two parties where there is a
sender or a sending party at one end, sending information and receiver or a receiving party at other end
(generally the sender party sends queries), after that the receiver side comes to an action, grasping it,
processing it and, acknowledging it back to the sender, this is how communication works.
Communication is a two-way process.

Natural Language Processing (NLP) is an exposure of AI that helps computers understand, interpret,
acknowledge and utilize human languages. NLP allows computers to communicate with homo sapiens,
using a human language. Natural Language Processing also provides computers with the ability to read
text, hear speech, and interpret it.
The study of natural language processing generally started in the 1950s, although some work can be
found from earlier periods. In 1950, Alan Turing wrote a paper describing a test for a “thinking”
machine. He stated that if a machine could be part of a conversation through the use of a teleprinter, and
it imitated a human so completely there were no noticeable differences, then the machine could be
considered capable of thinking. Furthermore, up to the 1980s, most NLP systems were based on complex
sets of hand-written rules. In the 1990s, the popularity of statistical models for NLP analyses rose
dramatically. As matter of fact, NLP has become the evergreen growing research field. Since the
ambiguity of data is the constant issue overall large-scale data processing. Also, every field is moving
towards automation to reduce human efforts. In that case, NLP helps the machine to learn the real-world
situation and understand human interaction for taking effective decisions over data.

After the Year 2000

In 2001, Yoshio Bengio and his team proposed the first neural network-based “language” model, using
a “Feedforward” network. A goal of statistical language modeling is to learn the joint probability
function of sequences of words in a language. In this type of network, data moves only in one direction,
from the input nodes, through the hidden nodes, and then to the output nodes. The feed-forward neural
network has no cycles or loops, and is quite different from recurrent neural networks.

In 2011, Apple’s Siri became known as one of the world’s first successful NLP / AI assistants to be used
by general consumers. Within Siri, the automated speech recognition module translates the owner’s
words into digitally interpreted concepts. By using machine learning techniques, the user’s speech
pattern does not have to exactly match predefined utterances. The sounds only have to be reasonably
close for a PLN system to translate the meaning correctly.

Where is NLP currently?

With the power of DL models, we can process text (understood as sequences of words or sequences of
characters which form the basis of human language), time series (weather data), and sequence data in
general. NLP growing in an exponential manner which has touched the mark of $ 16 billion by 2021
with the compound growth rate of 16 % annually. The reason behind this growth is rising of the
chatbots, urge of discovering the customer insights, transfer of technology of messaging from manual to
automated and many other tasks which are required to be automated and involve language/Speech at
some point. Though, as stated above the functionality revolves around language/speech which refers to
words in its basic raw form. No matter what is the medium of the communication, whether it is verbal or
written, words are the basic fundamental unit of the functionality. But currently there seems to be a
difference in the performance of NLP, when it is handling texts and when it is handling voice.
THE ROLE OF MACHINE LEARNING IN NLP:

We are living in an age where we simply need to speak to the VA (voice assistant) and command to get
things done for us. This is where NLP or Natural language processing with AI comes into the picture. As
the subset of machine learning. More importantly “machine learning” really means “machine
teaching.” We know what the machine needs to learn, so our task is to create a learning framework and
provide properly-formatted, relevant, clean data for the machine to learn from.

Machine learning for NLP and text analytics involves a set of statistical techniques for identifying parts
of speech, entities, sentiment, and other aspects of text. The techniques can be expressed as a model that
is then applied to other text, also known as supervised machine learning. It also could be a set of
algorithms that work across large sets of data to extract meaning, which is known as unsupervised
machine learning.

A machine learning model is the mathematical representation of the clean and relevant information that
the system is structured to learn from. This includes the sum of all the knowledge that the system has
gained from its intake of training data, the new knowledge and insights it gains as input and interactions
occur, and more learning occurs.

Machine learning models are typically designed with the ability to generalize and deal with new cases
and information. So, if a system encounters a situation resembling one of its past experiences, it can use
the previous learning it acquired in evaluating the new case. And as the system matures, it can
continuously improve, evolving and adapting to fresh input.

Language is continuously evolving, with new expressions, abbreviations, and usage patterns
emerging in response to changing social, economic, and political conditions. The data sets that NLP
systems have to deal with are also complex and increasing in volume. For natural language processing
machine learning provides a logical framework for data handling and the tools and flexibility needed for
dealing with a complex and demanding discipline.