The students will be able to learn: -
• Working of NLP
• Components of NLP
• NLP tasks and techniques
• Components and Applications of NLP
In this chapter, you will learn how to explore the digital world. Here’s a brief overview:
• Introduction to NLP: NLP bridges the gap by allowing machines to process and
understand human languages, making it an essential tool in modern AI systems.
• Working of NLP: Natural language processing (NLP) combines computational
linguistics, machine learning, and deep learning models to process human language.
Computational linguistics is the science of understanding and constructing human
language models with computers and software tools..
• NLP Components: These include text preprocessing, lexical analysis, syntactic
analysis, semantic analysis, discourse analysis, and pragmatic
analysis. Additionally, it incorporates machine learning, deep learning, and
various NLP techniques like tokenization, part-of-speech tagging, and named
entity recognition.
• Applications of NLP:. (NLP) has diverse applications, spanning from everyday
digital interactions to complex tasks like machine translation and sentiment
analysis. NLP powers tools like voice assistants, chatbots, search engines, and
language translation services, enabling machines to understand, interpret, and
generate human language.
A. Fill in the blanks: -
1. The Sentence Segmentation NLP technique is used to break the paragraph into
different sentences.
2. The Stemming NLP technique simplifies the word into its root word.
3. In sentiment analysis, the sentence “The movie is dreadful” is classified as
Negative sentiment.
4. NLG involves converting computerized text into natural language.
5. Email filters in applications like Gmail use the NLP technique called Keyword
extraction.
B. Write T for True and F for False.
1. Tokenisation is the last step of NLP technique.
2. Digital assistants like Alexa and Siri do not use NLP to interpret voice
commands.
3. Stemming and Lemmatisation are techniques used in NLP to simplify words.
4. Google Maps uses NLP to provide real-time traffic updates and directions
5. Named Entity Recognition involves extracting entities like names and places
from text.
C. Competency –based question.
Shruti’s grandmother wants to use a computer but finds it challenging to type and
navigate apps, like calendar, alarms, and photo album. Which device should Shruti
recommend that allows her grandmother to simply speak commands instead of
typing and manually browsing the applications?
Ans- Shruti should recommend a smart speaker, like Alexa or Siri.
D. Select the correct option.
1. Which technique breaks text into smaller chunks called tokens?
a. Tokenisation b. Stemming
c. Sentiment Analysis
2. Which application of NLP helps in converting speech to text?
a. Named Entity Recognition b. Speech Recognition
c. Parts of speech tagging
3. What is the purpose of Stop word removal in NLP?
a. To add affix to words b. To segment Sentences
c. To remove irrelevant words
4. What does NLP stand for?
a. National Language Processing
b. Natural Language Processing
c. Natural Linguistic Programme
5. Which of the following is not a component of NLP?
a. Natural Language Generation (NLG)
b. Natural Language Understanding (NLU)
c. Artificial Neural Networks (ANN)
E. Answer the following questions.
1. What is Natural Language Processing (NLP)?
Ans- The Natural Language Processing is a domain of AI that enables computers to
understand, interpret, and generate human language.
2. Describe the difference between Natural language understanding (NLU) and
Natural language generation (NLG).
Ans- NLU helps the machine to understand and analyses human language by
extracting the metadata from the content, like concept, keyword, emotions,
etc. Whereas, NLG acts as a translator that converts computerised text into
natural language.
3. Explain the role of Sentiment Analysis in understanding text data.
Ans- NLP can be used to analyse and understand the sentiment expressed in text
data, such as customer reviews, social media posts, or feedback.
