2021 1.

3 NLP Applications
 E23 NATURAL LANGUAGE PROCESSING

Unit 1
Introduction: Overview of NLP: Origins and challenges of NLP - Language and Grammar:
NLP Applications - Information Retrieval. Language Modeling: Various Grammar- based
Language Models-Statistical Language Model

3 APPLICATIONS OF NLP

3.1 COMMON APPLICATIONS OF NLP

In this section, we discuss some of the very useful applications of NLP.
1. Sentiment Analysis
2. Text Classification
3. Chatbots & Virtual Assistants
4. Text Extraction / IE / NER
5. Machine Translation
6. Text Summarization
7. Auto-Correct
8. Intent Classification
9. Urgency Detection
10. Speech Recognition
11. Information Retrieval
12. Question Answering System
13. Character Recognition
14. Text Prediction

1. Sentiment Analysis

Sentiment analysis, however, is able to recognize subtle nuances in emotions and opinions in
text and determine how positive or negative they are. This application is also known as
opinion mining. It is implemented through a combination of Natural Language Processing
and statistics by assigning values to the text (positive, negative or neutral) and in turn making
efforts to identify the underlying mood of the context (happy, sad, angry, annoyed, etc.)
This application of NLP helps business organisations gain insights on consumers and do a
competitive comparison and make necessary adjustments in business

2. Text Classification

Text classification, a text analysis task that also includes sentiment analysis, involves
automatically understanding, processing, and categorizing unstructured text.

Let’s say you want to analyze hundreds of open-ended responses to your recent NPS survey.
Doing it manually would take you a lot of time and end up being too expensive. But what if
you could train a natural language processing model to automatically tag your data in just
seconds, using predefined categories and applying your own criteria? You might use a topic
classifier for NPS survey responses, which automatically tags your data by topics
like Customer Support, Features, Ease of Use, and Pricing.

3. Chatbots & Virtual Assistants

Chatbots and virtual assistants are used for automatic question answering, designed to
understand natural language and deliver an appropriate response through natural language
generation.

Standard question answering systems follow pre-defined rules, while AI-powered chatbots
and virtual assistants are able to learn from every interaction and understand how they should
respond. The best part: they learn from interactions and improve over time. These intelligent
machines are increasingly present at the frontline of customer support, as they can help teams
solve up to 80% of all routine queries and route more complex issues to human agents.
Available 24/7, chatbots and virtual assistants can speed up response times, and relieve agents
from repetitive and time-consuming queries.

4. Text Extraction / IE / NER

Information Extraction (IE): These extractions can then be utilized for a range of applications
including question-answering, visualization, and data mining.

NER: This is also known as named entity recognition. You can also extract keywords within
a text, e.g. persons, companies, locations, organizations, from large collections of text.

IE focuses on the recognition, tagging, and extraction into a structured representation. You
might also want to use text extraction for data entry. You could pull out the information you
need and set up a trigger to automatically enter this information in your database.

5. Machine Translation

Machine translation (MT) is one of the first applications of natural language processing.
Machine translation has come a long way since its inception, mainly thanks to huge advances
in the field of neural networks and the increased availability of large amounts of data.

With NLP, online translators can translate languages more accurately and present
grammatically-correct results. This is infinitely helpful when trying to communicate with
someone in another language. Not only that, but when translating from another language to
your own, tools now recognize the language based on inputted text and translate it.

Automated translation is particularly useful in business because it facilitates communication,

allows companies to reach broader audiences, and understand foreign documentation in a fast
and cost-effective way.

6. Text Summarization

Automatic summarization is pretty self-explanatory. It summarizes text, by extracting the

most important information. Its main goal is to simplify the process of going through vast
amounts of data, such as scientific papers, news content, or legal documentation.

There are two ways of using natural language processing to summarize data: extraction-
based summarization ‒ which extracts keyphrases and creates a summary, without adding
any extra information ‒ and abstraction-based summarization, which creates new phrases
paraphrasing the original source. This second approach is more common and performs better.

7. Auto-Correct

Natural Language Processing plays a vital role in grammar checking software and auto-
correct functions. Tools like Grammarly, for example, use NLP to help you improve your
writing, by detecting grammar, spelling, or sentence structure errors.

8. Intent Classification

Intent classification consists of identifying the goal or purpose that underlies a text. Apart
from chatbots, intent detection can drive benefits in sales and customer support areas.

By analyzing customer interactions like emails, chats, or social media posts, you can spot
customers that are ready to purchase. The faster you can detect and classify those leads, the
more chances you have of turning them into customers.

9. Urgency Detection

NLP techniques can also help you detect urgency in text. You can train an urgency detection
model using your own criteria, so it can recognize certain words and expressions that denote
gravity or discontent. This can help you prioritize the most important requests and make sure
they don’t get buried under a pile of unresolved tickets.

Urgency detection helps you improve response times and efficiency, leading to a positive
impact on customer satisfaction.

10. Speech Recognition

Speech recognition technology uses natural language processing to transform spoken

language into a machine-readable format.

Speech recognition systems are an essential part of virtual assistants, like Siri, Alexa, and
Google Assistant, for example. However, there are more and more use cases of speech
recognition in business. For example, adding speech-to-text capabilities to business software,
companies are able to automatically transcribe calls, send emails, and even translate.

11. Information Retrieval (IR)

IR provides a list of potentially relevant documents in response to a user’s query.

12. Question-Answering Systems

Question-answering is a Computer Science discipline within the fields of AI and NLP. It

focuses on building systems that automatically answer questions posted by human beings in
their natural language. A computer system that understands the natural language has the
capability of a program system to translate the sentences written by humans into an internal
representation so that the valid answers can be generated by the system. The exact answers
can be generated by doing syntax and semantic analysis of the questions. Lexical gap,
ambiguity and multilingualism are some of the challenges for NLP in building good question
answering system. Applications such as Siri, OK Google, chat boxes and virtual assistants
are QAS.

13. Character Recognition

Optical Character Recognition (OCR) is the process of converting images of handwritten,

typed, or printed text into machine-encoded language. It is one of the commonly used
approaches to digitize printed texts so it can be saved, edited, searched electronically.

OCR and NLP combine to provide a range of benefits that can help businesses complete their
document-related tasks such as read and recognize ID cards/passports automatically, enter
data into various forms or CRMs, verify customer data gathered from various sources,
instantly scan bank cards, indices, cheques, tickets, etc.

14. Text Prediction

Text prediction refers to the process of estimating the next word in a phrase or sentence. One
of the popular and common examples of text prediction is Google Search.
Google uses BERT (Bidirectional Encoder Representations from Transformers), a Natural
Language Processing (NLP) algorithm that uses neural networks to create pre-trained models.
These models are trained using a huge amount of unannotated text available on the web. The
BERT algorithm helps the search engine to understand queries in a way similar to humans.
Other than this, many other applications such as Google Docs, Gmail Compose uses NLP
language models that help in text prediction.

3.2 DOMAIN-SPECIFIC APPLICATIONS

Hiring and Recruitment – By using natural language processing in hiring and

recruitment, candidate searches are sped up by filtering and sifting through resumes of
applicants that meet the job requirements. With a bias-proof, gender-neutral and relevant
synonyms of keywords for the job description by NLP-based software, recruiters can
maximize the number of job applicants without potential good candidates being neglected
in the search process.

Advertising – Natural language processing helps in the identification of new audiences

that are potentially interested in certain products. With the use of NLP software, the range
of channels for ad placements can be broadened which then helps the company maximize
and use their budget wisely especially when using simple keyword machine routine.

Customer Service – NLP-powered chatbots can provide customer service by answering

routine questions and handling simple requests. This allows increasing customer
satisfaction, especially that chatbots provide swift help in personalized conversations and
partially replacing humans in simple scenarios importantly providing customer support at
any time of the day.

Healthcare – With the help of health IT systems in the healthcare industry, providers and
doctors are accompanied by reduced subjectivity in decision-making and providing
relevant medical knowledge. There are many ways NLP is of help in the healthcare
industry. With NLP, data retrieval of patients is simplified and sped up making it easier to
access medical information. Aside from that, it also helps healthcare providers and doctors
make accurate decisions when it comes to treatment and diagnosis with the help of
predictive models.

Market Intelligence – Staying relevant in the market can be challenging but with NLP-
based, advanced tools, companies can filter through numerous blogs, websites, social
media posts to be updated with the current trend and what's going on in respective
industries. Insightful data can also be acquired thereby strengthening the company's
business and reducing dissatisfaction from potential customers.

Fraud Detection in Banking - The world of finance is very vulnerable to fraud and this
world solely based on the text as every entry and record is maintained in the form of text.
Natural Language Processing with the help of Machine Learning is used to detect
fraud and
misinterpreted information. Natural Language Processing generally used to extract
information and process information which is further used by Machine learning model to
train themselves to expose the fraud.

Défense and National Security- USA ‘s Defence Research and Analysis

wing DARPA (Defence Advanced Research Projects Agency) developed a program DEFT
(Deep Exploration and Filtering of Text) in which Natural Language Processing is used to
extract pertinent information from unstructured data. This information is further used to
analytics procedures to draw some insights from the data. Moreover, NLP based models also
used by the Institute for Strategic Dialogue in the United Kingdom to observe and trace the
signs of radicalization and extremism.