Scribd
Upload
22 views2 pages

Unit 1 Introduction To NLP Notes

Natural Language Processing (NLP) is a branch of AI that enables computers to understand human languages, evolving through three waves: rule-based systems, statistical methods, and deep learning. Challenges in NLP include ambiguity, context dependence, and understanding idioms, while its applications range from machine translation to chatbots. Key operations in NLP involve word analysis, syntax and semantic analysis, and information retrieval.

Uploaded by

Rushikesh Potgante
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
22 views2 pages

Unit 1 Introduction To NLP Notes

Natural Language Processing (NLP) is a branch of AI that enables computers to understand human languages, evolving through three waves: rule-based systems, statistical methods, and deep learning. Challenges in NLP include ambiguity, context dependence, and understanding idioms, while its applications range from machine translation to chatbots. Key operations in NLP involve word analysis, syntax and semantic analysis, and information retrieval.

Uploaded by

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

Unit 1: Introduction to Natural Language Processing (NLP)

Natural Language Processing (NLP) is a field of Artificial Intelligence (AI) focused on enabling
computers to understand and process human languages.

Three Waves of NLP


1. First Wave: Rationalism (1950s–1980s): Rule-based systems using symbolic logic. Example: ELIZA
chatbot.
2. Second Wave: Empiricism (1990s): Statistical methods using large corpora. Example: IBM’s
statistical machine translation.
3. Third Wave: Deep Learning (2010s): Neural networks like RNN, CNN, and Transformers. Example:
ChatGPT, BERT.

Why NLP is Difficult?


Ambiguity – e.g., 'I saw the man with the telescope'.
Context Dependence – e.g., 'He is cool'.
Syntax and Grammar Variations.
Named Entity Recognition (NER).
Understanding idioms, sarcasm – e.g., 'Oh great! Another Monday'.
Data Sparsity and Noisy Input.

Importance of NLP
Language Understanding, Information Extraction, Machine Translation, Speech Recognition, Question
Answering, etc.
Example: Alexa, Google Translate, chatbots.

Basic NLP Terminologies


Phonology: Study of sounds. Morphology: Word structure.
Syntax: Sentence structure. Semantics: Meaning.
Pragmatics: Intent. Discourse: Sentence connections.
Example: 'Can you pass the salt?' – a polite request, not a real question.

Basic NLP Operations


1. Word Level Analysis – e.g., Tokenization, Stemming: 'running' → 'run'
2. Syntax Analysis – Sentence structure.
3. Semantic Analysis – Word Sense Disambiguation: 'bank' (river vs finance).
4. Discourse Integration – Linking across sentences.
5. Pragmatic Analysis – understanding sarcasm, context, etc.

POS Tagging
Assigns part-of-speech like noun, verb, adjective to each word.
Example: 'Ram eats mangoes' → NNP VBZ NNS
Approaches: Rule-Based, Statistical (HMM), Neural Networks (RNN, LSTM)

Sequence Labeling
Each word in a sentence is assigned a label.
Example: 'John lives in Paris' → [B-PER, O, O, B-LOC]

Natural Language Inception


Recursive use of NLP to generate/analyze more language.
Example: GPT-generated text fed to another model, chatbot loops.

Information Retrieval (IR)


Finding relevant documents based on a query.
Steps: Indexing, Query Processing, Retrieval Models (BM25), Ranking, Evaluation.
Example: Google search.

Applications of NLP
Sentiment Analysis, Text Classification, NER, Machine Translation.
Chatbots, Summarization, Question Answering, Speech Recognition, Info Extraction.
Example: Zomato chatbot, YouTube subtitles, customer feedback analysis.

You might also like