[Solved] The following code tries to find the word most similar to king - man + woman but has a flaw:import numpy as np words = {'king': np.array([0.5, 0.8, 0.3]), 'queen': np.array([0.45, 0.75, 0.... | NLP

NLP - Word Embeddings

The following code tries to find the word most similar to king - man + woman but has a flaw:

import numpy as np
words = {'king': np.array([0.5, 0.8, 0.3]), 'queen': np.array([0.45, 0.75, 0.35]), 'man': np.array([0.6, 0.7, 0.2]), 'woman': np.array([0.55, 0.65, 0.25])}
result = words['king'] - words['man'] + words['woman']
max_word = None
max_sim = -1
for word, vec in words.items():
    sim = np.dot(result, vec) / (np.linalg.norm(result) * np.linalg.norm(vec))
    if sim > max_sim:
        max_word = word
print(max_word)

What is the main flaw?

AThe variable max_sim is initialized incorrectly

BDivision by zero occurs due to zero vector norm

CThe dot product is computed without normalizing vectors

DThe code does not exclude the original words from similarity search

Step-by-Step Solution

Solution:

Step 1: Analyze the similarity search loop
The loop compares the result vector to all words including 'king', 'man', and 'woman' which are part of the calculation.
Step 2: Understand why this is problematic
Including original words can cause the highest similarity to be the input words themselves, which is usually unwanted and can cause misleading results.
Final Answer:
The code does not exclude the original words from similarity search -> Option D
Quick Check:
Exclude input words to avoid bias [OK]

Quick Trick: Exclude input words from similarity search to avoid bias [OK]

Common Mistakes:

MISTAKES

Assuming zero division error without checking norms
Thinking max_sim initialization causes error
Ignoring normalization in dot product

Master "Word Embeddings" in NLP

9 interactive learning modes - each teaches the same concept differently

Learn Why Deep Model Try Challenge Experiment Recall Metrics

More NLP Quizzes

The following code tries to find the word most similar to king - man + woman but has a flaw:

Step 1: Analyze the similarity search loop

Step 2: Understand why this is problematic

Final Answer:

Quick Check:

Want More Practice?