Word similarity and analogies in NLP

Introduction

Word similarity and analogies help computers understand how words relate to each other, like how 'king' relates to 'queen'. This makes language tasks easier and smarter.

Finding words that mean similar things, like synonyms.

Answering analogy questions, such as 'man is to king as woman is to ?'.

Improving search engines to find related words.

Helping chatbots understand user questions better.

Organizing words by meaning in language learning apps.

Syntax

NLP

from gensim.models import KeyedVectors

# Load pre-trained word vectors
model = KeyedVectors.load_word2vec_format('path/to/word2vec.bin', binary=True)

# Find similarity between two words
similarity = model.similarity('word1', 'word2')

# Find words similar to a given word
similar_words = model.most_similar('word', topn=5)

# Solve analogy: word_a is to word_b as word_c is to ?
result = model.most_similar(positive=['word_b', 'word_c'], negative=['word_a'], topn=1)

You need pre-trained word vectors like Word2Vec or GloVe to use these methods.

Similarity returns a score between -1 and 1 showing how close two words are.

Examples

This finds how similar 'cat' and 'dog' are based on their meanings in the model.

NLP

similarity = model.similarity('cat', 'dog')
print(similarity)

This lists the top 3 words closest in meaning to 'king'.

NLP

similar_words = model.most_similar('king', topn=3)
print(similar_words)

This solves the analogy: 'man' is to 'king' as 'woman' is to ?

NLP

result = model.most_similar(positive=['woman', 'king'], negative=['man'], topn=1)
print(result)

Sample Model

This program loads a small word vector model, calculates similarity between 'cat' and 'dog', finds words similar to 'king', and solves a simple analogy.

NLP

from gensim.models import KeyedVectors

# Load a small pre-trained model for demonstration
# Here we use a small subset from gensim-data for quick testing
import gensim.downloader as api
model = api.load('glove-wiki-gigaword-50')

# Calculate similarity between 'cat' and 'dog'
similarity = model.similarity('cat', 'dog')
print(f"Similarity between 'cat' and 'dog': {similarity:.2f}")

# Find top 3 words similar to 'king'
similar_words = model.most_similar('king', topn=3)
print("Top 3 words similar to 'king':")
for word, score in similar_words:
    print(f"{word}: {score:.2f}")

# Solve analogy: man is to king as woman is to ?
result = model.most_similar(positive=['woman', 'king'], negative=['man'], topn=1)
print(f"'man' is to 'king' as 'woman' is to '{result[0][0]}' with score {result[0][1]:.2f}")

Important Notes

Pre-trained models can be large; using smaller ones helps beginners experiment quickly.

Not all words will be in the model vocabulary; check with 'word in model' before using.

Similarity scores closer to 1 mean very similar; closer to 0 or negative means less related.

Summary

Word similarity measures how close two words are in meaning using numbers.

Analogies let us find a word that fits a relationship between other words.

Pre-trained word vectors are needed to do these tasks easily.

Practice

1. What does word similarity measure in natural language processing?

easy

A. How close two words are in meaning using numbers

B. How often two words appear together in a sentence

C. The length difference between two words

D. The number of letters two words share

Solution

1. Step 1: Understand the concept of word similarity

   Word similarity measures how close two words are in meaning, often represented by a number like cosine similarity.

2. Step 2: Differentiate from other word properties

   Frequency or letter count does not capture meaning closeness, so those options are incorrect.

3. Final Answer:

   How close two words are in meaning using numbers -> Option A

4. Quick Check:

   Word similarity = meaning closeness [OK]

Hint: Similarity means meaning closeness, not letter or frequency count [OK]

Common Mistakes:

• Confusing similarity with word frequency
• Thinking similarity is about word length
• Assuming similarity counts shared letters

2. Which of the following is the correct way to find the cosine similarity between two word vectors vec1 and vec2 in Python using NumPy?

easy

A. np.dot(vec1, vec2) / (np.linalg.norm(vec1) * np.linalg.norm(vec2))

B. np.dot(vec1, vec2) * (np.linalg.norm(vec1) + np.linalg.norm(vec2))

C. np.dot(vec1, vec2) - (np.linalg.norm(vec1) * np.linalg.norm(vec2))

D. np.dot(vec1, vec2) / (np.linalg.norm(vec1) + np.linalg.norm(vec2))

Solution

1. Step 1: Recall cosine similarity formula

   Cosine similarity = dot product of vectors divided by product of their norms.

2. Step 2: Match formula to code

   np.dot(vec1, vec2) / (np.linalg.norm(vec1) * np.linalg.norm(vec2)) matches the formula exactly using np.dot and np.linalg.norm.

3. Final Answer:

   np.dot(vec1, vec2) / (np.linalg.norm(vec1) * np.linalg.norm(vec2)) -> Option A

4. Quick Check:

   Cosine similarity = dot / (norm1 * norm2) [OK]

Hint: Cosine similarity divides dot product by product of norms [OK]

Common Mistakes:

• Adding norms instead of multiplying
• Subtracting norms from dot product
• Multiplying dot product by sum of norms

3. Given the following word vectors:

king = [0.5, 0.8, 0.3]
queen = [0.45, 0.75, 0.35]
man = [0.6, 0.7, 0.2]
woman = [0.55, 0.65, 0.25]

What is the closest word to the vector king - man + woman?

medium

A. king

B. man

C. queen

D. woman

Solution

1. Step 1: Calculate the vector for king - man + woman

   Subtract man from king: [0.5-0.6, 0.8-0.7, 0.3-0.2] = [-0.1, 0.1, 0.1]. Add woman: [-0.1+0.55, 0.1+0.65, 0.1+0.25] = [0.45, 0.75, 0.35].

2. Step 2: Compare result to known vectors

   The resulting vector matches queen exactly: [0.45, 0.75, 0.35].

3. Final Answer:

   queen -> Option C

4. Quick Check:

   king - man + woman = queen [OK]

Hint: king - man + woman equals queen vector [OK]

Common Mistakes:

• Not subtracting man vector before adding woman
• Mixing up vector addition order
• Choosing original words instead of analogy result

4. 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?

medium

A. The variable max_sim is initialized incorrectly

B. Division by zero occurs due to zero vector norm

C. The dot product is computed without normalizing vectors

D. The code does not exclude the original words from similarity search

Solution

1. 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.

2. 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.

3. Final Answer:

   The code does not exclude the original words from similarity search -> Option D

4. Quick Check:

   Exclude input words to avoid bias [OK]

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

Common Mistakes:

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

5. You want to find the word that fits the analogy: Paris is to France as Tokyo is to ? Using pre-trained word vectors, which approach is best to find the answer?

hard

A. Calculate vector: France - Tokyo + Paris, then find closest word vector

B. Calculate vector: Tokyo - Paris + France, then find closest word vector

C. Calculate vector: Paris + France - Tokyo, then find closest word vector

D. Calculate vector: Tokyo + Paris - France, then find closest word vector

Solution

1. Step 1: Understand analogy vector arithmetic

   Analogies use the formula: word2 - word1 + word3 to find the missing word. Here, Paris is word1, France is word2, Tokyo is word3.

2. Step 2: Apply formula to this analogy

   Calculate Tokyo - Paris + France to get the vector representing the answer.

3. Final Answer:

   Calculate vector: Tokyo - Paris + France, then find closest word vector -> Option B

4. Quick Check:

   Analogy vector = word3 - word1 + word2 [OK]

Hint: Use analogy formula: word3 - word1 + word2 [OK]

Common Mistakes:

• Swapping order of subtraction and addition
• Adding all vectors without subtraction
• Using wrong words in formula