Why Beam search decoding in NLP? - Purpose & Use Cases

The Big Idea

What if choosing just one word at a time makes your computer miss the best story it could tell?

The Scenario

Imagine you want to find the best sentence a computer can generate word by word, but you try to pick each next word by guessing only the single most likely option every time.

This is like trying to write a story by always choosing the first word that comes to mind without considering other possibilities.

The Problem

This simple way often misses better sentences because it ignores other good options that might lead to a better overall result.

It's slow and frustrating to try all possible sentences manually, and easy to get stuck with poor choices early on.

The Solution

Beam search decoding keeps track of several best sentence options at once, not just one.

It explores multiple paths in parallel, balancing between exploring new possibilities and focusing on the most promising ones.

This way, it finds better sentences faster and more reliably.

Before vs After

✗ Before

next_word = max(probabilities)  # pick only the top word each step

✓ After

beams = keep_top_k_sequences(probabilities, k=3)  # track top 3 sequences at each step

What It Enables

Beam search decoding lets machines generate smarter, more natural sentences by exploring multiple good options simultaneously.

Real Life Example

When you use voice assistants or translation apps, beam search helps them choose the best way to say something, making the output clearer and more accurate.

Key Takeaways

Picking only the single best next word can miss better overall sentences.

Beam search tracks multiple good sentence options at once.

This leads to faster, more accurate sentence generation in language tasks.

Practice

1. What is the main purpose of beam search decoding in natural language processing?

easy

A. To keep track of multiple best candidate sequences during prediction

B. To randomly select words for output generation

C. To generate only one possible output sequence

D. To speed up training by skipping steps

Solution

1. Step 1: Understand beam search goal

   Beam search keeps multiple candidate sequences to explore more options than greedy search.

2. Step 2: Compare options

   Only To keep track of multiple best candidate sequences during prediction describes keeping multiple best guesses; others describe random choice, single output, or unrelated speed-up.

3. Final Answer:

   To keep track of multiple best candidate sequences during prediction -> Option A

4. Quick Check:

   Beam search = multiple best sequences [OK]

Hint: Beam search tracks several top guesses, not just one [OK]

Common Mistakes:

• Confusing beam search with random sampling
• Thinking beam search outputs only one sequence
• Assuming beam search speeds up training

2. Which of the following is the correct way to describe the beam width in beam search decoding?

easy

A. The size of the vocabulary used for prediction

B. The number of candidate sequences kept at each decoding step

C. The length of the output sequence generated

D. The number of layers in the neural network

Solution

1. Step 1: Define beam width

   Beam width is how many top sequences the algorithm keeps at each step to explore.

2. Step 2: Eliminate incorrect options

   Output length, vocabulary size, and network layers are unrelated to beam width.

3. Final Answer:

   The number of candidate sequences kept at each decoding step -> Option B

4. Quick Check:

   Beam width = candidate count per step [OK]

Hint: Beam width = how many sequences you keep each step [OK]

Common Mistakes:

• Mixing beam width with output length
• Confusing beam width with vocabulary size
• Thinking beam width relates to model architecture

3. Consider a beam search with beam width 2 decoding a sequence. At step 1, the top 2 tokens have scores [0.6, 0.4]. At step 2, each token expands to two tokens with scores: from first token [0.5, 0.3], from second token [0.7, 0.2]. Which two sequences will beam search keep after step 2?

medium

A. [First token + second expansion (0.6*0.3), Second token + second expansion (0.4*0.2)]

B. [First token + first expansion (0.6*0.5), First token + second expansion (0.6*0.3)]

C. [Second token + first expansion (0.4*0.7), Second token + second expansion (0.4*0.2)]

D. [First token + first expansion (0.6*0.5), Second token + first expansion (0.4*0.7)]

Solution

1. Step 1: Calculate scores for all expansions

   Calculate combined scores: 0.6*0.5=0.3, 0.6*0.3=0.18, 0.4*0.7=0.28, 0.4*0.2=0.08.

2. Step 2: Select top 2 sequences by score

   Top two scores are 0.3 and 0.28, corresponding to first token + first expansion and second token + first expansion.

3. Final Answer:

   [First token + first expansion (0.6*0.5), Second token + first expansion (0.4*0.7)] -> Option D

4. Quick Check:

   Top scores = 0.3 and 0.28 [OK]

Hint: Multiply scores, pick top beam width sequences [OK]

Common Mistakes:

• Choosing expansions only from one token
• Not multiplying scores correctly
• Picking lower scoring sequences

4. You implemented beam search decoding but notice it always returns the same output sequence regardless of input. What is the most likely bug?

medium

A. The vocabulary size is too large

B. The model is not trained

C. Beam width is set to 1, making it greedy search

D. The beam search is not normalizing scores

Solution

1. Step 1: Analyze symptom of identical outputs

   Always same output suggests no exploration of multiple sequences.

2. Step 2: Identify beam width effect

   If beam width = 1, beam search reduces to greedy search, always picking highest scoring token only.

3. Final Answer:

   Beam width is set to 1, making it greedy search -> Option C

4. Quick Check:

   Beam width 1 = greedy search [OK]

Hint: Check beam width; 1 means no beam search [OK]

Common Mistakes:

• Blaming vocabulary size for output sameness
• Ignoring beam width setting
• Assuming model training causes identical outputs

5. In a machine translation task, you want to balance output quality and decoding speed. You have a beam search decoder with beam width 5. What happens if you increase the beam width to 20?

hard

A. Output quality may improve but decoding will be slower

B. Output quality will decrease and decoding will be faster

C. Output quality and decoding speed remain the same

D. Decoding speed improves but output quality is unpredictable

Solution

1. Step 1: Understand beam width effect on quality

   Larger beam width explores more sequences, often improving output quality.

2. Step 2: Understand beam width effect on speed

   More sequences to track means more computation, slowing decoding speed.

3. Final Answer:

   Output quality may improve but decoding will be slower -> Option A

4. Quick Check:

   Higher beam width = better quality, slower speed [OK]

Hint: Bigger beam = better results but slower decoding [OK]

Common Mistakes:

• Assuming bigger beam always speeds decoding
• Thinking quality decreases with bigger beam
• Believing beam width doesn't affect speed