PGoCareerGoCareer prep tools
Home
LoginSign up
  • Java
  • Python
  • AI
  • React
  • Angular
  • PHP
  • Node.js
  • SQL
  • DSA
  • HTML
  • CSS
  • JS
  • Spring
  • ML
  • MongoDB

AI · Theory

Natural Language Processing

← All stacks

Theory

49/215

Natural Language Processing

NLP is AI for human language: text or speech. Levels: tokens → syntax → meaning → dialogue. Tasks: classification (spam), translation, NER, Q&A, summarisation, chat. Today: transformers / large language models. Still fail on sarcasm, rare words, and invented facts (hallucination).

Tiny start: split “Asha got 90 marks” into tokens. That is not understanding yet. Don’t jump to GPT without saying tokens and a task.

Natural Language Processing — output — ['asha', 'got', '90', 'marks'] then a reminder. Classification/chat comes after.

Diagram
text
    │ tokenize
    ▼
  tokens → task
    (class / translate / chat)
Exam tip

One task + one failure mode.

Example

# NLP start — tokenize
text = "Asha got 90 marks"
tokens = text.lower().split()
print(tokens)
print("tokens ≠ understanding")

Natural Language Processing — output: ['asha', 'got', '90', 'marks'] then a reminder. Classification/chat comes after.

Short notes

  • DefMachines + human language.
  • Tasks : class / translate / NER / chat.
  • Traphallucination.

Questions

1

Explain Natural Language Processing as if you are teaching a junior — definition, then one example.

2

What does the example print, and what does that prove?

3

What mistake do freshers make with Natural Language Processing?

Previous← Expert SystemsNextAI in Education →
P

GoCareerGo

Utilities · Preparation Hub · Resume · CV · Tools — one workspace.

Workspace

DashboardProfilePreparation HubResume builderCV builderCareer planning

PDF Tools

Merge PDFSplit PDFCompress PDFImage to PDFAll toolsJobs

Image & QR

Compress ImageResize ImageQR ScannerQR GeneratorBlogIT interview prep

Company

FAQFeedbackContactPrivacyTermsSitemap

© 2026 GoCareerGo. Keep moving forward.