Evaluating generated text (BLEU, ROUGE) in NLP - Cheat Sheet & Quick Revision

Recall & Review

beginner

What does BLEU score measure in text generation?

BLEU (Bilingual Evaluation Understudy) measures how closely the generated text matches one or more reference texts by comparing overlapping n-grams.

beginner

What is ROUGE used for in evaluating generated text?

ROUGE (Recall-Oriented Understudy for Gisting Evaluation) measures the overlap of units such as n-grams, word sequences, and word pairs between the generated text and reference summaries, focusing on recall.

intermediate

Why is BLEU considered precision-oriented while ROUGE is recall-oriented?

BLEU focuses on how much of the generated text matches the reference (precision), while ROUGE focuses on how much of the reference text is covered by the generated text (recall).

beginner

What is an n-gram in the context of BLEU and ROUGE?

An n-gram is a sequence of 'n' words in a row. For example, a 2-gram (bigram) is two consecutive words. Both BLEU and ROUGE compare these sequences between generated and reference texts.

intermediate

How does BLEU handle multiple reference texts?

BLEU compares the generated text against multiple reference texts and uses the best matching n-grams from any reference to calculate the score, improving evaluation accuracy.

What does a high BLEU score indicate?

A The generated text is very different from the reference

B The generated text closely matches the reference text

C The generated text is longer than the reference

D The generated text has many spelling errors

A high BLEU score means the generated text shares many n-grams with the reference, indicating close similarity.

Which metric is more focused on recall in text evaluation?

A BLEU

B F1 Score

C Accuracy

D ROUGE

ROUGE emphasizes recall by measuring how much of the reference text is captured by the generated text.

What is an n-gram?

A A sequence of n words in a row

B A single word

C A type of neural network

D A punctuation mark

An n-gram is a continuous sequence of n words used to compare texts.

Which of these is true about BLEU?

A It measures recall of generated text

B It only works with one reference text

C It measures precision of generated text

D It ignores word order

BLEU measures precision by checking how much generated text matches reference n-grams.

ROUGE is commonly used to evaluate which type of generated text?

A Text summarization

B Speech recognition

C Machine translation

D Image captioning

ROUGE is widely used to evaluate summaries by comparing them to reference summaries.

Explain how BLEU and ROUGE differ in evaluating generated text.

Think about what each metric focuses on: matching generated text vs. covering reference text.

Describe what an n-gram is and why it is important for BLEU and ROUGE.

Consider how small word groups help check if texts are similar.

Practice

1. What is the main purpose of BLEU and ROUGE scores in evaluating generated text?

easy

A. To measure how similar the generated text is to human-written text

B. To check the spelling errors in generated text

C. To count the number of words in the generated text

D. To translate text from one language to another

Solution

1. Step 1: Understand the role of BLEU and ROUGE

   Both BLEU and ROUGE are metrics used to compare generated text with reference human text to check similarity.

2. Step 2: Identify the main purpose

   They do not check spelling, count words, or translate text but measure similarity to human text.

3. Final Answer:

   To measure how similar the generated text is to human-written text -> Option A

4. Quick Check:

   BLEU and ROUGE measure similarity [OK]

Hint: Remember: BLEU and ROUGE check similarity, not spelling or translation [OK]

Common Mistakes:

• Confusing BLEU/ROUGE with spell check
• Thinking they count words only
• Assuming they translate text

2. Which of the following is the correct way to calculate BLEU score using Python's nltk library?

easy

A. bleu_score = nltk.bleu_score([candidate], reference)

B. bleu_score = nltk.translate.bleu_score.sentence_bleu([reference], candidate)

C. bleu_score = nltk.translate.bleu_score([candidate], [reference])

D. bleu_score = nltk.score.bleu(candidate, reference)

Solution

1. Step 1: Recall the nltk BLEU function syntax

   The correct function is sentence_bleu from nltk.translate.bleu_score, which takes a list of references and a candidate sentence.

2. Step 2: Match the correct syntax

   bleu_score = nltk.translate.bleu_score.sentence_bleu([reference], candidate) uses sentence_bleu([reference], candidate), which is the correct call format.

3. Final Answer:

   bleu_score = nltk.translate.bleu_score.sentence_bleu([reference], candidate) -> Option B

4. Quick Check:

   Use sentence_bleu with list of references [OK]

Hint: Use sentence_bleu with references as a list [OK]

Common Mistakes:

• Passing candidate as first argument instead of second
• Not wrapping reference in a list
• Using wrong module or function name

3. Given the following code snippet, what will be the printed BLEU score?

from nltk.translate.bleu_score import sentence_bleu
reference = [['the', 'cat', 'is', 'on', 'the', 'mat']]
candidate = ['the', 'cat', 'sat', 'on', 'the', 'mat']
score = sentence_bleu(reference, candidate)
print(round(score, 2))

medium

A. 0.92

B. 0.75

C. 0.58

D. 0.33

Solution

1. Step 1: Understand BLEU calculation basics

   BLEU compares n-gram overlap; here, candidate differs by one word ('sat' vs 'is'), so score is high but not perfect.

2. Step 2: Run or estimate BLEU score

   Running this code yields approximately 0.916, rounded to 0.92.

3. Final Answer:

   0.92 -> Option A

4. Quick Check:

   BLEU score close to 1 means high similarity [OK]

Hint: BLEU near 1 means very similar sentences [OK]

Common Mistakes:

• Assuming exact match needed for high BLEU
• Confusing BLEU with ROUGE
• Ignoring n-gram overlap effect

4. You wrote code to compute ROUGE-L score but get an error: AttributeError: module 'rouge' has no attribute 'Rouge'. What is the likely cause?

medium

A. The input texts are empty strings

B. ROUGE-L score cannot be computed in Python

C. The 'rouge' package is not installed or imported incorrectly

D. You must use BLEU instead of ROUGE-L

Solution

1. Step 1: Analyze the error message

   The error says the module 'rouge' has no attribute 'Rouge', indicating the package or import is missing or incorrect.

2. Step 2: Understand correct usage

   You need to install the correct 'rouge' package and import Rouge class properly to use ROUGE-L.

3. Final Answer:

   The 'rouge' package is not installed or imported incorrectly -> Option C

4. Quick Check:

   AttributeError usually means missing or wrong import [OK]

Hint: Check package installation and import statements first [OK]

Common Mistakes:

• Assuming ROUGE-L can't be computed in Python
• Ignoring installation errors
• Using wrong package names

5. You have two text generation models. Model A has a BLEU score of 0.45 and ROUGE-L score of 0.60. Model B has a BLEU score of 0.55 and ROUGE-L score of 0.50. Which model should you prefer if you want better phrase matching and why?

hard

A. Model A, because lower BLEU means better phrase matching

B. Model A, because higher ROUGE-L means better phrase matching

C. Model B, because lower ROUGE-L means better phrase matching

D. Model B, because higher BLEU means better phrase matching

Solution

1. Step 1: Understand BLEU and ROUGE focus

   BLEU focuses on phrase matching; ROUGE-L focuses on longest common subsequence (word overlap).

2. Step 2: Compare scores for phrase matching

   Model B has higher BLEU (0.55) than Model A (0.45), so Model B is better for phrase matching.

3. Final Answer:

   Model B, because higher BLEU means better phrase matching -> Option D

4. Quick Check:

   Higher BLEU = better phrase matching [OK]

Hint: BLEU = phrase match; ROUGE = word overlap [OK]

Common Mistakes:

• Confusing BLEU and ROUGE meanings
• Choosing model with higher ROUGE for phrase matching
• Ignoring which metric matches the goal