BLEU score evaluation in NLP - Model Metrics & Evaluation

Metrics & Evaluation - BLEU score evaluation

Which metric matters for BLEU score evaluation and WHY

BLEU score measures how close a machine-generated text is to human-written text. It checks if the words and phrases match well. This helps us know if a translation or text generation is good. BLEU focuses on matching small groups of words (called n-grams) between the output and reference. The higher the BLEU score (from 0 to 1), the better the match.

Confusion matrix or equivalent visualization

BLEU does not use a confusion matrix like classification. Instead, it counts matching n-grams between the candidate and reference texts.

Reference:  "the cat is on the mat"
Candidate:  "the cat sat on the mat"

Unigram matches: the, cat, on, the, mat (5 matches)
Bigram matches: the cat, on the, the mat (3 matches)

BLEU score combines these matches with a penalty for short sentences.
    

Precision vs Recall tradeoff with concrete examples

BLEU mainly measures precision: how many words in the candidate appear in the reference. It does not measure recall (how many reference words appear in candidate). This means a candidate can have high BLEU by repeating common words even if it misses some meaning.

Example:

• Candidate: "the the the the the" (high precision on "the" but poor meaning)
• Candidate: "cat is on mat" (misses some words but still matches key phrases)

BLEU uses a brevity penalty to avoid very short outputs scoring too high.

What "good" vs "bad" BLEU scores look like for this use case

BLEU scores range from 0 to 1 (often shown as 0 to 100%).

• Good BLEU: Above 0.5 (50%) usually means the output is quite close to human text.
• Moderate BLEU: Around 0.3 to 0.5 means some matching but room to improve.
• Bad BLEU: Below 0.2 means poor match, likely bad translation or text.

Note: BLEU is best used to compare models, not as an absolute quality measure.

Common pitfalls in BLEU score evaluation

• BLEU ignores meaning and grammar; it only checks word overlap.
• High BLEU does not always mean good quality text.
• BLEU favors shorter n-grams; longer phrase matches are harder to get.
• Using only one reference text can limit BLEU's reliability.
• BLEU does not measure recall, so missing important words is not penalized enough.

Self-check question

Your machine translation model has a BLEU score of 0.65. Is this good? Why or why not?

Answer: A BLEU score of 0.65 is generally good, showing strong overlap with human translations. However, you should also check the actual text quality because BLEU does not capture meaning or grammar perfectly.

Key Result

BLEU score measures n-gram precision to evaluate text similarity, with higher scores indicating closer match to human reference.

Practice

1. What does the BLEU score primarily measure in machine translation?

easy

A. How close the machine translation is to human translations

B. The speed of the translation process

C. The number of words in the translated sentence

D. The grammar correctness of the translation

Solution

1. Step 1: Understand BLEU score purpose

   BLEU score is designed to compare machine translations to human reference translations.

2. Step 2: Identify what BLEU measures

   It measures similarity in words and phrases, not speed or grammar correctness.

3. Final Answer:

   How close the machine translation is to human translations -> Option A

4. Quick Check:

   BLEU = similarity to human translations [OK]

Hint: BLEU = closeness to human translation quality [OK]

Common Mistakes:

• Confusing BLEU with translation speed
• Thinking BLEU measures grammar correctness
• Assuming BLEU counts total words only

2. Which of the following is the correct way to calculate the BLEU score using NLTK in Python?

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.translate.bleu_score.score(candidate, reference)

Solution

1. Step 1: Recall NLTK BLEU function syntax

   The correct function is sentence_bleu and it takes a list of references and a candidate sentence.

2. Step 2: Match correct argument order

   References must be a list of lists, candidate is a list of tokens.

3. Final Answer:

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

4. Quick Check:

   Use sentence_bleu([ref], cand) syntax [OK]

Hint: Use sentence_bleu with references as list of lists [OK]

Common Mistakes:

• Passing candidate before reference
• Not wrapping reference in a list
• Using incorrect function names

3. Given the candidate sentence ["the", "cat", "is", "on", "the", "mat"] and reference sentence ["there", "is", "a", "cat", "on", "the", "mat"], what is the approximate BLEU score (unigram precision only)?

medium

A. 0.83

B. 0.50

C. 0.67

D. 0.33

Solution

1. Step 1: Calculate unigram matches

   Candidate words: the, cat, is, on, the, mat
   Reference words: there, is, a, cat, on, the, mat
   Matching unigrams: the, cat, is, on, mat (count matches carefully)

2. Step 2: Compute unigram precision

   Matches = 5 (the counted once), Candidate length = 6
   Precision = 5/6 ≈ 0.83 but 'the' appears twice in candidate but once in reference, so max count for 'the' is 1.
   Counting max matches: 'the' once, 'cat' once, 'is' once, 'on' once, 'mat' once = 5 matches
   Precision = 5/6 ≈ 0.83

3. Step 3: Adjust for max counts

   Since 'the' appears twice in candidate but only once in reference, only one 'the' counts.
   So total matches = 5, candidate length = 6, precision = 5/6 ≈ 0.83

4. Final Answer:

   0.83 -> Option A

5. Quick Check:

   Unigram precision = 5/6 = 0.83 [OK]

Hint: Count max reference word matches for unigram precision [OK]

Common Mistakes:

• Counting repeated words more than reference max
• Confusing unigram with bigram precision
• Ignoring max count clipping

4. Identify the error in this BLEU score calculation code snippet:

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(score)

medium

A. Candidate should be a string, not a list

B. Missing import for nltk

C. Reference should be a list of lists, not a single list

D. sentence_bleu requires lowercase strings only

Solution

1. Step 1: Check sentence_bleu input format

   sentence_bleu expects references as a list of reference sentences (each a list of tokens), so reference must be wrapped in another list.

2. Step 2: Identify the error in code

   Reference is given as a single list, not a list of lists, causing a type error or wrong calculation.

3. Final Answer:

   Reference should be a list of lists, not a single list -> Option C

4. Quick Check:

   References = list of lists [OK]

Hint: Wrap reference in a list for sentence_bleu [OK]

Common Mistakes:

• Passing reference as a flat list
• Passing candidate as string instead of list
• Ignoring input format requirements

5. You have two reference translations:
ref1 = ['the', 'cat', 'is', 'on', 'the', 'mat']
ref2 = ['there', 'is', 'a', 'cat', 'on', 'the', 'mat']
And a candidate translation:
candidate = ['the', 'cat', 'sat', 'on', 'the', 'mat']
How should you prepare the references to correctly compute the BLEU score considering multiple references?

hard

A. Pass references as separate calls to sentence_bleu

B. Concatenate ref1 and ref2 into a single list and pass as one reference

C. Pass only the reference closest in length to candidate

D. Pass references as a list containing both ref1 and ref2 lists

Solution

1. Step 1: Understand multiple references in BLEU

   BLEU supports multiple references by passing a list of reference sentences (each a list of tokens).

2. Step 2: Prepare references correctly

   References should be passed as [ref1, ref2], a list containing both reference lists.

3. Step 3: Avoid incorrect methods

   Concatenating references or passing separately will give wrong results.

4. Final Answer:

   Pass references as a list containing both ref1 and ref2 lists -> Option D

5. Quick Check:

   Multiple references = list of reference lists [OK]

Hint: Use list of reference lists for multiple references [OK]

Common Mistakes:

• Concatenating references into one list
• Passing references separately in multiple calls
• Using only one reference when multiple exist