Extractive summarization in NLP - Model Pipeline Trace

Model Pipeline - Extractive summarization

Extractive summarization picks important sentences from a text to make a shorter summary. It keeps original sentences without changing words.

Data Flow - 6 Stages

1Data in

1000 documents x variable length text→Raw text documents collected for summarization→1000 documents x variable length text

"The cat sat on the mat. It was sunny outside. The dog barked loudly."

↓

2Preprocessing

1000 documents x variable length text→Split text into sentences, clean punctuation and lowercase→1000 documents x average 10 sentences

["the cat sat on the mat", "it was sunny outside", "the dog barked loudly"]

↓

3Feature Engineering

1000 documents x 10 sentences→Convert sentences to vectors using TF-IDF or embeddings→1000 documents x 10 sentences x 300 features

[[0.1, 0.0, ..., 0.3], [0.0, 0.2, ..., 0.1], ...]

↓

4Model Training

1000 documents x 10 sentences x 300 features→Train classifier to score sentence importance→1000 documents x 10 sentences x 1 score

[0.8, 0.3, 0.6, 0.1, ...]

↓

5Metrics Improve

Scores and reference summaries→Calculate ROUGE scores to evaluate summary quality→ROUGE-1: 0.45, ROUGE-2: 0.30, ROUGE-L: 0.40

ROUGE-1 F1 score = 0.45

↓

6Prediction

New document x 10 sentences x 300 features→Score sentences and select top 3 for summary→Summary with 3 sentences

"The cat sat on the mat. The dog barked loudly. It was sunny outside."

Training Trace - Epoch by Epoch

Loss
0.7 |****
0.6 |*** 
0.5 |**  
0.4 |*   
0.3 |    
     1 2 3 4 5 Epochs

Epoch	Loss ↓	Accuracy ↑	Observation
1	0.65	0.60	Model starts learning to identify important sentences
2	0.50	0.72	Loss decreases, accuracy improves as model learns better
3	0.40	0.80	Model shows good improvement in sentence scoring
4	0.35	0.85	Training converges with stable loss and high accuracy
5	0.33	0.87	Final epoch with best performance on training data

Prediction Trace - 4 Layers

Layer 1: Sentence vectorization

Layer 2: Sentence scoring

Layer 3: Sentence selection

Layer 4: Summary output

Model Quiz - 3 Questions

What does the model output after training?

A Scores indicating sentence importance

B New sentences generated from scratch

C Only the first sentence of the document

D Random sentences unrelated to the text

Key Insight

Extractive summarization models learn to score sentences by importance and select the top ones to create a concise summary without changing original text. Training improves sentence scoring accuracy and reduces loss steadily.

Practice

1. What is the main goal of extractive summarization in NLP?

easy

A. To translate the text into another language

B. To rewrite the text using simpler words

C. To select important sentences from the original text to create a summary

D. To generate new sentences that explain the text

Solution

1. Step 1: Understand extractive summarization

   Extractive summarization picks key sentences directly from the original text without changing them.

2. Step 2: Compare options

   Only To select important sentences from the original text to create a summary describes selecting important sentences from the original text, which matches extractive summarization.

3. Final Answer:

   To select important sentences from the original text to create a summary -> Option C

4. Quick Check:

   Extractive summarization = selecting key sentences [OK]

Hint: Extractive means picking from original text directly [OK]

Common Mistakes:

• Confusing extractive with abstractive summarization
• Thinking it rewrites or translates text
• Assuming it generates new sentences

2. Which of the following is a common technique used in extractive summarization?

easy

A. Neural machine translation

B. Text generation with GPT

C. Part-of-speech tagging

D. TF-IDF scoring of sentences

Solution

1. Step 1: Identify techniques for extractive summarization

   Extractive summarization often uses TF-IDF to score sentences by importance based on word frequency.

2. Step 2: Eliminate unrelated options

   Neural machine translation and text generation are for other NLP tasks, and POS tagging is not directly used for summarization scoring.

3. Final Answer:

   TF-IDF scoring of sentences -> Option D

4. Quick Check:

   TF-IDF = common extractive technique [OK]

Hint: TF-IDF ranks sentence importance in extractive summarization [OK]

Common Mistakes:

• Confusing summarization with translation or generation
• Thinking POS tagging directly creates summaries
• Ignoring TF-IDF's role in scoring

3. Given the following Python code snippet using TF-IDF for extractive summarization, what will be the output?

from sklearn.feature_extraction.text import TfidfVectorizer

texts = ["Cats are great pets.", "Dogs are loyal animals.", "Cats and dogs can live together."]
vectorizer = TfidfVectorizer()
X = vectorizer.fit_transform(texts)
scores = X.sum(axis=1)
print(scores)

medium

A. [[0.0], [0.0], [0.0]]

B. [[2.0], [2.0], [2.4]]

C. [[2.0], [2.0], [3.0]]

D. [[1.0], [1.0], [1.0]]

Solution

1. Step 1: Understand TF-IDF vectorization and summing

   The code vectorizes three sentences and sums TF-IDF scores per sentence (row-wise sum).

2. Step 2: Calculate approximate sums

   Each sentence has TF-IDF scores summing roughly to 2.0, 2.0, and 2.4 respectively due to shared and unique words.

3. Final Answer:

   [[2.0], [2.0], [2.4]] -> Option B

4. Quick Check:

   Sum TF-IDF per sentence ≈ [[2.0], [2.0], [2.4]] [OK]

Hint: Sum TF-IDF scores per sentence to get importance [OK]

Common Mistakes:

• Assuming zero scores for all sentences
• Confusing sum with average
• Misunderstanding TF-IDF output shape

4. You have this extractive summarization code snippet:

sentences = ["AI is fascinating.", "It helps solve problems.", "AI can learn from data."]
scores = [0.8, 0.9, 0.85]
summary = []
for i in range(len(sentences)):
    if scores[i] > 0.85:
        summary.append(sentences[i])
print(summary)

What is the output and is there any bug?

medium

A. ['It helps solve problems.'] with no bug

B. ['AI is fascinating.', 'It helps solve problems.', 'AI can learn from data.'] with no bug

C. ['It helps solve problems.', 'AI can learn from data.'] but index error bug

D. [] because scores are not compared correctly

Solution

1. Step 1: Check score filtering condition

   The code adds sentences with scores > 0.85, so sentences with 0.9 and 0.85 are checked; 0.85 is not > 0.85, so only 0.9 and 0.85 fail or pass accordingly.

2. Step 2: Determine which sentences are included

   Scores: 0.8 (no), 0.9 (yes), 0.85 (no). So only "It helps solve problems." is included. But 0.85 is not > 0.85, so excluded.

3. Final Answer:

   ['It helps solve problems.'] -> Option A

4. Quick Check:

   Scores > 0.85 filter sentences correctly [OK]

Hint: Check strict > vs >= in score filtering [OK]

Common Mistakes:

• Including sentences with score equal to threshold
• Expecting index errors where none exist
• Misreading the comparison operator

5. You want to create an extractive summarizer that picks the top 2 sentences from a document based on TF-IDF scores. Given these sentences and their scores:

sentences = ["Machine learning is fun.", "It allows computers to learn.", "Summarization helps understand text.", "TF-IDF ranks sentence importance."]
scores = [0.7, 0.9, 0.6, 0.8]

Which two sentences should your summarizer select?

hard

A. ["It allows computers to learn.", "TF-IDF ranks sentence importance."]

B. ["Machine learning is fun.", "Summarization helps understand text."]

C. ["Summarization helps understand text.", "TF-IDF ranks sentence importance."]

D. ["Machine learning is fun.", "It allows computers to learn."]

Solution

1. Step 1: Identify top 2 scores

   The scores are 0.7, 0.9, 0.6, 0.8. The top two are 0.9 and 0.8.

2. Step 2: Match scores to sentences

   0.9 corresponds to "It allows computers to learn.", 0.8 corresponds to "TF-IDF ranks sentence importance.".

3. Final Answer:

   ["It allows computers to learn.", "TF-IDF ranks sentence importance."] -> Option A

4. Quick Check:

   Top 2 scores = 0.9 and 0.8 sentences [OK]

Hint: Pick sentences with highest TF-IDF scores [OK]

Common Mistakes:

• Choosing sentences with lower scores
• Mixing up sentence-score pairs
• Selecting more or fewer than top 2