Part-of-Speech (POS) Tagging
• Finds the type of each word in a sentence.
• Identifies words as nouns, verbs, adjectives, etc.
• Helps understand sentence structure easily.
• Makes text analysis more accurate.
• Solves confusion in word meanings.
• Improves translation between languages.
• Helps in speech recognition systems.
• Extracts useful language patterns.
• Makes computers understand human language better.
• Important for working with text data.
Difference Between Natural and Programming Languages
| **Natural Language** | **Programming Language** |
| Used for speaking and writing | Used for coding and commands |
| Changes and grows naturally | Has fixed structure and rules |
| Can have multiple meanings | Always has clear meaning |
| Uses informal words | Uses strict logic and syntax |
| Different in every culture | Same for all computers |
| For human communication | For machine instructions |
| Can change over time | Follows set rules strictly |
| Learned through interaction | Learned with study and practice |
| Many words, flexible grammar | Few words, fixed grammar |
| Expresses emotions, feelings | Gives exact instructions |
Tokenization
• Breaks text into small parts.
• Needed for working with text.
• Word tokenization separates words.
• Sentence tokenization separates sentences.
• Subword tokenization splits long words.
• Character tokenization separates letters.
• Helps understand rare or new words.
• Improves language models.
• Makes text processing easier.
• Useful in translation and analysis.
What is natural language processing (NLP)? Discuss various stages
Involved in NLP process with suitable example.
• NLP helps computers understand human language.
• It reads and processes text and speech.
• Tokenization breaks text into small parts.
• Stop word removal deletes common useless words.
• Stemming changes words to their basic form.
• Parsing checks sentence grammar structure.
• Named Entity Recognition finds important names.
• Sentiment analysis understands emotions in text.
• Translation changes text into other languages.
• Chatbots talk to people using NLP.
• Machine learning improves NLP performance.
• NLP turns language into computer-readable data.
Discuss the challenges of Natural Language Processing.
• Words with many meanings confuse NLP.
• Understanding context makes meaning hard.
• Detecting sarcasm is very tricky.
• Many languages make learning tough.
• Not enough data limits learning.
• Idioms confuse word-by-word reading.
• Big models need strong computers.
• Messy data reduces learning accuracy.
• Adapting to new fields is hard.
• Bias in data affects fairness.
• Machines’ decisions are hard to explain.
• Mixing text, speech, and images is tough.
Explain Derivational and Inflectional morphology in detail with
suitable Example.
• Derivational changes make new word meanings.
• Prefixes, suffixes change word type, meaning.
• “Happy” becomes “happiness” by derivation.
• Derivation makes adjectives from noun words.
• It strongly changes word meanings always.
• Word groups grow using derivational endings.
• Inflection changes words for grammar rules.
• It changes tense, number using endings.
• “Walk” becomes “walks” by inflection.
• Inflection keeps the word type same.
• Plurals form using inflectional endings.
• Inflection keeps main word meaning unchanged.
Morphology and Morphemes
• Morphology studies how words are formed.
• It looks at roots, stems, and affixes.
• Stem is the main part of a word.
• Affix adds extra meaning to a word.
• Prefix comes before a word’s main part.
• Suffix comes after and changes meaning.
• Example: “unhappy” has prefix “un” + “happy”.
• Some affixes go inside or around words.
• Stems are important for word building.
• Studying morphemes helps understand word structure.
Context-Free Grammar (CFG)
• CFG helps define sentence structure clearly.
• Nonterminals are placeholders for sentence parts.
• Terminals are the actual words used.
• CFG uses rules to form sentences.
• Example: “S → NP VP” splits sentences.
• NP (noun phrase) and VP (verb phrase) help.
• CFG makes language easier to understand.
• Rules continue until real words appear.
• CFG helps build and analyze sentences.
• It helps computers process human language.
Semantic Analysis Techniques
• Semantic analysis finds sentence meaning.
• Word sense disambiguation clears word confusion.
• Semantic role labeling assigns word roles.
• Named entity recognition finds important names.
• Ontology mapping connects words to knowledge.
• Distributional semantics learns from word context.
• Frame semantics understands words in situations.
• Logical form conversion gives sentence structure.
• Statistical models measure word similarity.
• Compositional semantics builds meaning from parts.
Probabilistic Parsing & PCFGs
• PCFGs use probabilities in grammar rules.
• Rules get chances based on data.
• Parsing becomes smart and data-driven.
• Probabilities help fix sentence confusion.
• It picks best sentence structure.
• Choices depend on most likely meaning.
• More data makes parsing better.
• Helps understand unclear sentence meanings.
• PCFGs improve language processing tasks.
• It links probabilities with sentence rules.
• Parsing makes sentence understanding easy.
• Models learn from many sentence examples.
Word Meaning Relationships with Examples
• Homonyms sound same, mean different things.
• Bank can mean money or river.
• Same word, totally different meanings.
• Polysemy means related multiple meanings.
• Head means leader or body part.
• Word changes meaning in different uses.
• Synonyms are different words, same meaning.
• Big and large mean the same.
• Use different words, say same thing.
• Hyponyms are specific word types.
• Rose is a type of flower.
• Shows word groups and their relations.
• Antonyms show opposite meanings.
• Hot and cold are opposites.
• Hypernyms are general category words.
• Animal is a category for dogs.
• Meronyms show part-whole relationships.
• A wheel is part of a car.