Beam search decoding in NLP

Introduction

Beam search decoding helps find the best possible output sequence from a model by exploring multiple options at once, instead of just one. It balances between trying many possibilities and keeping the search manageable.

When generating sentences in language translation to get better translations.

When creating text with AI chatbots to find the most meaningful replies.

When predicting sequences like speech or handwriting recognition outputs.

When you want a good balance between quality and speed in sequence generation.

Syntax

NLP

import math
def beam_search_decoder(predictions, beam_width):
    sequences = [[[], 0.0]]
    for row in predictions:
        all_candidates = []
        for seq, score in sequences:
            for j, prob in enumerate(row):
                if prob > 0:
                    candidate = [seq + [j], score - math.log(prob)]
                    all_candidates.append(candidate)
        ordered = sorted(all_candidates, key=lambda tup: tup[1])
        sequences = ordered[:beam_width]
    return sequences

The predictions input is usually a list of probability distributions for each step in the sequence.

beam_width controls how many sequences to keep at each step; bigger means better results but slower.

Examples

Runs beam search on two steps with two possible tokens each, keeping top 2 sequences.

NLP

beam_search_decoder([[0.1, 0.9], [0.8, 0.2]], beam_width=2)

Runs beam search with beam width 1, which is like greedy search (only best at each step).

NLP

beam_search_decoder([[0.3, 0.7, 0.0], [0.4, 0.4, 0.2]], beam_width=1)

Sample Model

This program runs beam search decoding on a small example with 3 steps and 3 tokens each. It prints the top 2 sequences found and their scores.

NLP

import math

def beam_search_decoder(predictions, beam_width):
    sequences = [[[], 0.0]]  # sequences and their scores (negative log probabilities)
    for row in predictions:
        all_candidates = []
        for seq, score in sequences:
            for j, prob in enumerate(row):
                if prob > 0:
                    candidate = [seq + [j], score - math.log(prob)]
                    all_candidates.append(candidate)
        sequences = sorted(all_candidates, key=lambda tup: tup[1])[:beam_width]
    return sequences

# Example predictions: 3 steps, 3 possible tokens each
predictions = [
    [0.1, 0.6, 0.3],
    [0.3, 0.5, 0.2],
    [0.4, 0.4, 0.2]
]
beam_width = 2
results = beam_search_decoder(predictions, beam_width)

print("Top sequences and their scores:")
for seq, score in results:
    print(f"Sequence: {seq}, Score: {score:.4f}")

Important Notes

Beam search is not guaranteed to find the absolute best sequence but usually finds a good one faster than trying all possibilities.

Using log probabilities helps avoid very small numbers and makes multiplication into addition.

Choosing beam width is a trade-off: bigger means better results but slower computation.

Summary

Beam search keeps multiple best guesses at each step to find good output sequences.

It balances quality and speed by limiting how many sequences it tracks.

It is widely used in language tasks like translation and text generation.

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