Document similarity ranking in NLP - Model Pipeline Trace

Model Pipeline - Document similarity ranking

This pipeline finds how similar documents are to a query document. It ranks documents by similarity scores, helping find the closest matches.

Data Flow - 6 Stages

1Data in

1000 documents x variable length text→Raw text documents collected for similarity search→1000 documents x variable length text

"Doc1: The cat sat on the mat.", "Doc2: Dogs are friendly animals."

↓

2Preprocessing

1000 documents x variable length text→Lowercase, remove punctuation, tokenize words→1000 documents x list of tokens

"doc1: ['the', 'cat', 'sat', 'on', 'the', 'mat']"

↓

3Feature Engineering

1000 documents x list of tokens→Convert tokens to TF-IDF vectors→1000 documents x 5000 features

Doc1 vector: [0.1, 0.0, 0.3, ..., 0.0]

↓

4Model Training

Training pairs of document vectors with similarity labels→Train a cosine similarity model or neural network to score similarity→Trained similarity scoring model

Model learns to output higher scores for similar document pairs

↓

5Metrics Improve

Validation document pairs→Evaluate ranking metrics like Mean Average Precision (MAP)→MAP score improves from 0.5 to 0.85

Epoch 1 MAP=0.5, Epoch 5 MAP=0.85

↓

6Prediction

Query document vector and 999 document vectors→Compute similarity scores and rank documents→Ranked list of documents by similarity

Query: Doc1, Top matches: Doc5 (0.92), Doc20 (0.89), Doc3 (0.85)

Training Trace - Epoch by Epoch

Loss
0.7 |****
0.6 |*** 
0.5 |**  
0.4 |**  
0.3 |*   
0.2 |*   
0.1 |    
    +-----
     1 5  Epochs

Epoch	Loss ↓	Accuracy ↑	Observation
1	0.65	0.55	Model starts learning, loss high, accuracy low
2	0.48	0.68	Loss decreases, accuracy improves
3	0.35	0.78	Model learns better similarity patterns
4	0.28	0.83	Loss continues to drop, accuracy rises
5	0.22	0.87	Model converges with good accuracy

Prediction Trace - 3 Layers

Layer 1: Query document vectorization

Layer 2: Similarity scoring

Layer 3: Ranking

Model Quiz - 3 Questions

What happens to the data shape after converting text to TF-IDF vectors?

A From numeric vectors to raw text

B From variable length text to fixed length numeric vectors

C From fixed length vectors to variable length text

D No change in data shape

Key Insight

Document similarity ranking uses vector representations and similarity scores to find and order documents by how close their meaning is to a query. Training improves the model's ability to assign higher scores to truly similar documents, making search results more relevant.

Practice

1. What does document similarity ranking help us do in natural language processing?

easy

A. Find how related two texts are based on their content

B. Translate documents into different languages

C. Summarize long documents into short ones

D. Detect spelling errors in documents

Solution

1. Step 1: Understand the purpose of document similarity ranking

   Document similarity ranking is used to compare texts and find how closely related they are based on their content.

2. Step 2: Identify the correct description

   Among the options, only finding relatedness of texts matches the purpose of document similarity ranking.

3. Final Answer:

   Find how related two texts are based on their content -> Option A

4. Quick Check:

   Document similarity ranking = Find related texts [OK]

Hint: Think: similarity means how close or related texts are [OK]

Common Mistakes:

• Confusing similarity ranking with translation
• Thinking it summarizes documents
• Mixing it up with spell checking

2. Which of the following is the correct way to compute cosine similarity between two vectors A and B in Python using NumPy?

easy

A. np.dot(A, B) * (np.linalg.norm(A) + np.linalg.norm(B))

B. np.dot(A, B) / (np.linalg.norm(A) * np.linalg.norm(B))

C. np.dot(A, B) - (np.linalg.norm(A) * np.linalg.norm(B))

D. np.dot(A, B) / (np.linalg.norm(A) + np.linalg.norm(B))

Solution

1. Step 1: Recall cosine similarity formula

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

2. Step 2: Match formula to code

   np.dot(A, B) / (np.linalg.norm(A) * np.linalg.norm(B)) correctly implements this formula using np.dot and np.linalg.norm.

3. Final Answer:

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

4. Quick Check:

   Cosine similarity formula = np.dot(A, B) / (np.linalg.norm(A) * np.linalg.norm(B)) [OK]

Hint: Cosine similarity = dot product ÷ (norm A x norm B) [OK]

Common Mistakes:

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

3. Given the following Python code using TF-IDF and cosine similarity, what will be the printed similarity score between the two documents?

from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.metrics.pairwise import cosine_similarity

docs = ['apple orange banana', 'banana fruit apple']
vectorizer = TfidfVectorizer()
X = vectorizer.fit_transform(docs)
sim_score = cosine_similarity(X[0], X[1])[0][0]
print(round(sim_score, 2))

medium

A. 0.50

B. 1.00

C. 0.58

D. 0.00

Solution

1. Step 1: Understand TF-IDF vectorization of similar documents

   Both documents share words 'apple' and 'banana' and have similar content, so their TF-IDF vectors will be close.

2. Step 2: Calculate cosine similarity between vectors

   Cosine similarity between these vectors will be high but less than 1, approximately 0.58 after rounding.

3. Final Answer:

   0.58 -> Option C

4. Quick Check:

   Similarity of similar docs ≈ 0.58 [OK]

Hint: Similar docs have cosine similarity close to 1 but not exactly 1 [OK]

Common Mistakes:

• Assuming similarity is exactly 1 for similar texts
• Confusing cosine similarity with Euclidean distance
• Ignoring TF-IDF weighting effects

4. The following code attempts to compute cosine similarity between two documents but raises an error. What is the main issue?

from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.metrics.pairwise import cosine_similarity

docs = ['cat dog', 'dog mouse']
vectorizer = TfidfVectorizer()
X = vectorizer.fit_transform(docs).toarray()
sim_score = cosine_similarity(X[0], X[1])
print(sim_score)

medium

A. cosine_similarity expects 2D arrays, but X[0] and X[1] are 1D arrays

B. TfidfVectorizer cannot process documents with different words

C. cosine_similarity requires dense arrays, not sparse matrices

D. The print statement has a typo in variable name

Solution

1. Step 1: Check input types for cosine_similarity

   cosine_similarity expects 2D arrays, but X[0] and X[1] are 1D arrays (shape (n_features,)).

2. Step 2: Understand how to fix the error

   Use X[0:1] and X[1:2] or reshape them properly to avoid the error.

3. Final Answer:

   cosine_similarity expects 2D arrays, but X[0] and X[1] are 1D arrays -> Option A

4. Quick Check:

   cosine_similarity input shape = 2D arrays [OK]

Hint: cosine_similarity needs 2D arrays, not single vectors [OK]

Common Mistakes:

• Thinking TfidfVectorizer fails on different words
• Thinking cosine_similarity accepts 1D arrays
• Overlooking variable name typos

5. You have a collection of 3 documents: ['apple banana', 'banana orange', 'apple orange banana']. You want to rank these documents by similarity to the query 'banana apple'. Which approach correctly ranks them from most to least similar using TF-IDF and cosine similarity?

hard

A. Use raw word counts without TF-IDF, rank by Euclidean distance ascending

B. Count word overlaps between query and documents, rank by overlap count ascending

C. Compute TF-IDF vectors but rank by cosine similarity scores ascending

D. Compute TF-IDF vectors for all documents and query, then rank by cosine similarity scores descending

Solution

1. Step 1: Understand ranking by similarity

   To rank documents by similarity to a query, compute vector representations and measure similarity scores, then sort descending (highest similarity first).

2. Step 2: Identify correct method

   TF-IDF vectors and cosine similarity are standard; ranking by descending cosine similarity scores is correct.

3. Final Answer:

   Compute TF-IDF vectors for all documents and query, then rank by cosine similarity scores descending -> Option D

4. Quick Check:

   Similarity ranking = cosine similarity descending [OK]

Hint: Rank documents by highest cosine similarity to query [OK]

Common Mistakes:

• Ranking by ascending similarity (lowest first)
• Using raw counts without weighting
• Ranking by overlap count ascending