Scribd
Upload
4 views

Introduction_to_NLP

Uploaded by

saratabassum043
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
4 views

Introduction_to_NLP

Uploaded by

saratabassum043
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 9

Introduction to Natural Language

Processing (NLP)
Understanding, Progress,
Applications, and Challenges
What is NLP?
• Natural Language Processing (NLP) is a field of
Artificial Intelligence.
• - It enables machines to read, understand, and
derive meaning from human language.
• - Core focus: Interaction between computers
and human (natural) languages.
Why NLP?
• NLP addresses the complexity of human
communication:
• - Extracts value from vast unstructured data
(e.g., conversations, tweets).
• - Enables scaling of analysis across massive
datasets.
• Key Challenges:
• - Understanding complex sentence structures
and meanings.
• - Ambiguity in language.
Applications of NLP
• NLP is widely used in various domains:
• - Chatbots (e.g., virtual assistants like Siri,
Alexa).
• - Speech Recognition.
• - Machine Translation (e.g., Google Translate).
• - Spell Checking and Keyword Searching.
• - Information Extraction and Advertisement
Matching.
Components of NLP
• 1. Natural Language Understanding (NLU):
• - Analyzing input language to derive meaning.
• - Involves: Morphological, Syntactic, Semantic,
and Discourse Analysis.

• 2. Natural Language Generation (NLG):


• - Creating human-like text from structured
data.
• - Includes: Deep Planning, Syntactic
NLP Pipeline
• Steps to build an NLP pipeline:
• - Tokenization: Splitting text into words or
phrases.
• - Stemming: Reducing words to their root
forms.
• - Lemmatization: Grouping inflected words
into base forms.
• - Part-of-Speech (POS) Tagging: Identifying
grammatical roles.
• - Named Entity Recognition (NER): Detecting
Phases of NLP
• 1. Morphological and Lexical Analysis:
• - Breaking text into sentences and words.

• 2. Syntactic Analysis:
• - Analyzing sentence structure and grammar.

• 3. Semantic Analysis:
• - Extracting literal meanings.
Challenges in NLP
• Ambiguity and complexity make NLP difficult:
• - Lexical Ambiguity: Words with multiple
meanings.
• - Syntactic Ambiguity: Multiple interpretations
of sentence structure.
• - Referential Ambiguity: Unclear references
using pronouns.
Grammars and Parsing
• 1. Context-Free Grammar (CFG):
• - Defines rules for forming valid sentences.

• 2. Parsing:
• - Analyzing sentence structure using parse
trees.
• - Techniques: Top-Down and Bottom-Up
Parsing.

You might also like