Course/Module 6/Topic 2 of 4Beginner

Word Embeddings

Understand word embeddings and their role in NLP.

60 min•By Priygop Team•Last updated: Feb 2026

What are Word Embeddings?

Word embeddings map words into dense vectors, capturing semantic relationships.

Popular Techniques

Word2Vec
GloVe
FastText
Transformers (BERT embeddings)

Implementation with Gensim

Example

from gensim.models import Word2Vec

sentences = [["natural", "language", "processing"], ["machine", "learning", "is", "fun"]]
model = Word2Vec(sentences, vector_size=50, window=5, min_count=1, workers=4)

print(model.wv['natural'])

Try It Yourself — Word Embeddings

Try It Yourself — Word EmbeddingsJavaScript

JavaScript Editor

✓ ValidTab = 2 spaces

// AI & Machine Learning concepts in JavaScript
// Simple linear regression simulation

// Training data: [hours studied] -> [score]
const data = [
  [1, 50], [2, 55], [3, 65], [4, 70],
  [5, 75], [6, 80], [7, 85], [8, 90],
];

// Calculate linear regression (y = mx + b)
function linearRegression(data) {
  const n = data.length;
  const sumX = data.reduce((s, [x]) => s + x, 0);
  const sumY = data.reduce((s, [, y]) => s + y, 0);
  const sumXY = data.reduce((s, [x, y]) => s + x * y, 0);
  const sumX2 = data.reduce((s, [x]) => s + x * x, 0);
  const m = (n * sumXY - sumX * sumY) / (n * sumX2 - sumX * sumX);
  const b = (sumY - m * sumX) / n;
  return { m, b };
}

const { m, b } = linearRegression(data);
console.log(`Model: score = ${m.toFixed(2)} * hours + ${b.toFixed(2)}`);

// Predict
function predict(hours) {
  return Math.round(m * hours + b);
}

console.log("Predictions:");
[3, 5, 7, 10].forEach(h => {
  console.log(`  ${h} hours → predicted score: ${predict(h)}`);
});