Unit I: Introduction to Natural Language
1. Applications of NLP
Natural Language Processing (NLP) is used in various real-world applications, such as:
- Machine Translation (e.g., Google Translate)
- Sentiment Analysis (e.g., Product reviews, Social media)
- Speech Recognition (e.g., Siri, Google Assistant)
- Chatbots and Virtual Assistants (e.g., ChatGPT)
- Text Summarization
- Named Entity Recognition (NER)
- Question Answering Systems
2. Language Understanding Systems
Language understanding systems attempt to interpret and derive meaning from human
language.
They typically include:
- Tokenization
- Part-of-Speech Tagging
- Syntax Analysis
- Semantic Analysis
- Pragmatic Analysis
3. Study of Language
Linguistics is the scientific study of language. Key areas relevant to NLP include:
- Phonology: Sounds of language
- Morphology: Structure of words
- Syntax: Sentence structure
- Semantics: Meaning of words and sentences
- Pragmatics: Contextual meaning
4. Syntactic and Semantic Analysis
Syntactic Analysis (Parsing) determines grammatical structure using rules and parse trees.
Semantic Analysis assigns meanings to syntactic structures.
Example:
Sentence: "Ram eats mango"
- Syntax Tree: [Subject] [Verb] [Object]
- Semantics: Eating is an action with an agent (Ram) and an object (mango).
5. Linguistic Background
Understanding the structure and function of language is foundational in NLP. Grammar
rules, vocabulary, and corpus-based learning help build robust NLP systems.
Linguistics supports formal models like Context-Free Grammars (CFGs) and Finite State
Automata (FSA).