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.