ROUGE evaluation metrics in NLP - Practice Problems & Coding Challenges

Challenge - 5 Problems

🧠 Conceptual

intermediate

Understanding ROUGE-N metric

What does the ROUGE-N metric primarily measure in text summarization evaluation?

A The semantic similarity using word embeddings

B The grammatical correctness of the generated summary

C The length difference between generated and reference summaries

D The overlap of n-grams between the generated summary and reference summary

💡 Hint

Think about what 'n-gram' means and what ROUGE-N counts.

ROUGE-N measures how many n-grams (continuous sequences of words) in the generated summary appear in the reference summary, showing overlap.

❓ Predict Output

intermediate

ROUGE-1 score calculation output

Given the following Python code snippet calculating ROUGE-1 recall, what is the printed output?

NLP

from collections import Counter

def rouge_1_recall(candidate, reference):
    candidate_tokens = candidate.split()
    reference_tokens = reference.split()
    ref_counts = Counter(reference_tokens)
    cand_counts = Counter(candidate_tokens)
    overlap = sum(min(cand_counts[w], ref_counts[w]) for w in cand_counts)
    recall = overlap / len(reference_tokens)
    return recall

candidate = "the cat sat on the mat"
reference = "the cat is on the mat"
print(round(rouge_1_recall(candidate, reference), 2))

A 0.83

B 0.67

C 0.71

D 0.57

💡 Hint

Count overlapping words and divide by total reference words.

The overlapping words are 'the', 'cat', 'on', 'the', 'mat' (5 tokens). Reference length is 6 tokens. Recall = 5/6 ≈ 0.83.

❓ Model Choice

advanced

Choosing ROUGE variant for phrase-level matching

You want to evaluate summaries focusing on matching longer phrases rather than single words. Which ROUGE variant is best suited?

A ROUGE-1

B ROUGE-S

C ROUGE-2

D ROUGE-L

💡 Hint

Consider which metric uses 2-grams (pairs of words).

ROUGE-2 measures overlap of 2-word sequences (bigrams), capturing phrase-level matches better than ROUGE-1 which uses single words.

❓ Metrics

advanced

Interpreting ROUGE-L score meaning

What does a high ROUGE-L score indicate about the generated summary compared to the reference?

A The generated summary shares many common subsequences with the reference, preserving sentence structure

B The generated summary has many matching individual words but in different order

C The generated summary is much shorter than the reference

D The generated summary uses synonyms of the reference words

💡 Hint

ROUGE-L uses longest common subsequence (LCS) to evaluate.

ROUGE-L measures the longest common subsequence, so a high score means the generated summary preserves word order and structure similar to the reference.

🔧 Debug

expert

Identifying error in ROUGE-2 precision calculation code

What error does the following code raise when calculating ROUGE-2 precision?

NLP

from collections import Counter

def rouge_2_precision(candidate, reference):
    def bigrams(text):
        return [text[i:i+2] for i in range(len(text)-1)]
    candidate_bigrams = bigrams(candidate.split())
    reference_bigrams = bigrams(reference.split())
    cand_counts = Counter(candidate_bigrams)
    ref_counts = Counter(reference_bigrams)
    overlap = sum(min(cand_counts[bg], ref_counts[bg]) for bg in cand_counts)
    precision = overlap / len(candidate_bigrams)
    return precision

candidate = "the cat sat on the mat"
reference = "the cat is on the mat"
print(round(rouge_2_precision(candidate, reference), 2))

A ZeroDivisionError

B No error, outputs 0.60

C TypeError

D IndexError

💡 Hint

Check if candidate_bigrams list is empty before division.

The code correctly computes bigrams and counts overlap. Candidate has 5 bigrams, overlap is 3, so precision = 3/5 = 0.60.

Practice

1. What does the ROUGE metric primarily measure in natural language processing?

easy

A. The sentiment of the generated text

B. The speed of text generation

C. The overlap between generated text and reference text

D. The grammatical correctness of text

Solution

1. Step 1: Understand ROUGE's purpose

   ROUGE is designed to compare generated text with a reference to check similarity.

2. Step 2: Identify what ROUGE measures

   It measures how much the generated text overlaps with the reference text in terms of words or sequences.

3. Final Answer:

   The overlap between generated text and reference text -> Option C

4. Quick Check:

   ROUGE = overlap measure [OK]

Hint: ROUGE checks text similarity, not speed or grammar [OK]

Common Mistakes:

• Confusing ROUGE with grammar checkers
• Thinking ROUGE measures sentiment
• Assuming ROUGE measures generation speed

2. Which of the following is the correct way to calculate ROUGE-1 recall?

easy

A. Number of overlapping unigrams divided by total unigrams in generated text

B. Number of overlapping unigrams divided by total unigrams in reference text

C. Number of overlapping bigrams divided by total bigrams in generated text

D. Number of overlapping bigrams divided by total bigrams in reference text

Solution

1. Step 1: Recall definition in ROUGE-1

   Recall measures how much of the reference text's unigrams appear in the generated text.

2. Step 2: Apply recall formula

   Recall = overlapping unigrams / total unigrams in reference text.

3. Final Answer:

   Number of overlapping unigrams divided by total unigrams in reference text -> Option B

4. Quick Check:

   Recall = overlap/reference [OK]

Hint: Recall divides by reference text count, not generated [OK]

Common Mistakes:

• Mixing up recall with precision
• Using generated text count in recall
• Confusing unigrams with bigrams

3. Given the reference text: "the cat sat on the mat" and generated text: "the cat lay on rug", what is the ROUGE-1 precision score?

medium

A. 0.6

B. 0.5

C. 0.4

D. 0.7

Solution

1. Step 1: Identify overlapping unigrams

   Common words: "the", "cat", "on". Overlapping unigrams = 3: "the", "cat", "on".

2. Step 2: Calculate precision

   Precision = overlapping unigrams / total unigrams in generated text = 3 / 5 = 0.6.

3. Final Answer:

   0.6 -> Option A

4. Quick Check:

   Precision = 3/5 = 0.6 [OK]

Hint: Precision = overlap / generated text words count [OK]

Common Mistakes:

• Counting duplicates incorrectly
• Using reference text length for precision
• Ignoring repeated words in calculation

4. You wrote code to compute ROUGE-L but the scores are always zero. Which of these is the most likely bug?

medium

A. Calculating precision instead of recall

B. Using ROUGE-1 instead of ROUGE-L

C. Using lowercase text for both inputs

D. Not tokenizing the texts before comparison

Solution

1. Step 1: Understand ROUGE-L calculation

   ROUGE-L depends on longest common subsequence of tokens, so tokenization is essential.

2. Step 2: Identify impact of missing tokenization

   If texts are not tokenized, comparison fails, resulting in zero scores.

3. Final Answer:

   Not tokenizing the texts before comparison -> Option D

4. Quick Check:

   Tokenization missing = zero ROUGE-L [OK]

Hint: Always tokenize texts before ROUGE-L calculation [OK]

Common Mistakes:

• Skipping tokenization step
• Confusing ROUGE types
• Ignoring case normalization impact

5. You want to evaluate a summarization model using ROUGE scores. The model produces very short summaries missing many reference words. Which ROUGE metric and score should you focus on to best understand coverage?

hard

A. ROUGE-1 recall, because it shows how many reference words are captured

B. ROUGE-1 precision, because it shows how many generated words are correct

C. ROUGE-L F1, because it balances precision and recall on longest sequences

D. ROUGE-2 precision, because it focuses on bigram accuracy

Solution

1. Step 1: Understand the problem context

   The summaries are short and miss many reference words, so coverage of reference is low.

2. Step 2: Choose metric that measures coverage

   Recall measures how much of the reference text is captured by the summary, so ROUGE-1 recall is best.

3. Final Answer:

   ROUGE-1 recall, because it shows how many reference words are captured -> Option A

4. Quick Check:

   Coverage = recall = ROUGE-1 recall [OK]

Hint: Use ROUGE-1 recall to check coverage of reference words [OK]

Common Mistakes:

• Focusing on precision instead of recall
• Using ROUGE-2 which is stricter
• Ignoring recall's role in coverage