Program: 2
Use dimensionality reduction (e.g., PCA or t-SNE) to visualize word embeddings for Q 1. a
specific domain (e.g., sports, technology) and visualize their embeddings. Analyze clusters
and relationships. Generate contextually rich outputs using embeddings. Write a program to
generate 5 semantically Select 10 words from similar words for a given input.
Title
Exploring Word Relationships and Visualizing Word Embeddings using Word2Vec
Aim
To perform word analogy operations using Word2Vec and visualize semantic relationships using
PCA and t-SNE techniques.
Software Requirements
Python 3.x
Gensim
NumPy
Matplotlib
Scikit-learn
Theory
Word2Vec is a neural network-based model that converts words into dense vector
representations. Semantic relationships between words can be discovered using vector
arithmetic. Dimensionality reduction techniques such as PCA and t-SNE help visualize high-
dimensional embeddings in 2D space.
Algorithm
Import required libraries.
Load pre-trained Word2Vec model.
Accept three words as input.
Perform vector arithmetic:
word1 − word2 + word3
Find most similar words using cosine similarity.
Remove input words from results.
Collect word vectors for visualization.
Reduce dimensions using PCA and t-SNE.
Plot words on a 2D graph.
Source Code:
Continue….
Continue……
Continue….
Output:
Continue….
Continue….
Viva Questions
1. What is Word2Vec?
2. Difference between CBOW and Skip-Gram?
3. Why is dimensionality reduction required?
4. Difference between PCA and t-SNE?
5. What similarity measure is used in Word2Vec?
Result
The semantic relationship between words was successfully identified using Word2Vec. PCA and
t-SNE visualizations clearly demonstrate meaningful word clusters.
Applications
Natural Language Processing
Information Retrieval
Recommendation Systems
Chatbots and Virtual Assistants