Beam search decoding in NLP - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to initialize the beam width for beam search decoding.

NLP

beam_width = [1]

Drag options to blanks, or click blank then click option'

A5

B1

C0

D10

Attempts:

3 left

💡 Hint

Common Mistakes

Setting beam width to 0 disables beam search.

Using 1 makes beam search behave like greedy search.

The beam width controls how many candidate sequences are kept at each step. A typical value is 10.

2fill in blank

medium

Complete the code to select the top scoring sequences at each decoding step.

NLP

top_sequences = sorted(all_candidates, key=lambda x: x.score, reverse=[1])[:beam_width]

Drag options to blanks, or click blank then click option'

ANone

B0

CTrue

DFalse

Attempts:

3 left

💡 Hint

Common Mistakes

Using reverse=False sorts ascending, which keeps worst sequences.

Using None or 0 causes errors or unexpected sorting.

We sort candidates in descending order of score, so reverse=True is needed.

3fill in blank

hard

Fix the error in the code that updates the beam with new candidates.

NLP

beam = [1]

Drag options to blanks, or click blank then click option'

Atop_sequences

Ball_candidates

Cbeam + all_candidates

D[]

Attempts:

3 left

💡 Hint

Common Mistakes

Assigning beam to all_candidates keeps too many sequences.

Using beam + all_candidates duplicates sequences.

Assigning beam to [] empties the beam.

The beam should be updated to the top scoring sequences only, not all candidates or an empty list.

4fill in blank

hard

Fill both blanks to complete the loop that expands sequences and applies beam search.

NLP

for step in range(max_length):
    all_candidates = []
    for seq in beam:
        next_tokens = model.predict(seq.sequence)
        for token, score in next_tokens.items():
            candidate = seq.sequence + [token]
            candidate_score = seq.score [1] score
            all_candidates.append(Candidate(candidate, candidate_score))
    beam = sorted(all_candidates, key=lambda x: x.score, reverse=[2])[:beam_width]

Drag options to blanks, or click blank then click option'

A+

B-

CTrue

DFalse

Attempts:

3 left

💡 Hint

Common Mistakes

Subtracting scores instead of adding.

Sorting ascending (reverse=False) loses best sequences.

We add the new token score to the sequence score, and sort descending (reverse=True) to keep best sequences.

5fill in blank

hard

Fill all three blanks to complete the beam search decoding function.

NLP

def beam_search_decode(model, start_token, beam_width, max_length):
    beam = [Candidate([start_token], 0.0)]
    for _ in range(max_length):
        all_candidates = []
        for seq in beam:
            next_tokens = model.predict(seq.sequence)
            for token, score in next_tokens.items():
                candidate = seq.sequence + [[1]]
                candidate_score = seq.score [2] score
                all_candidates.append(Candidate(candidate, candidate_score))
        beam = sorted(all_candidates, key=lambda x: x.score, reverse=[3])[:beam_width]
    return beam

Drag options to blanks, or click blank then click option'

Atoken

B+

CTrue

Dseq

Attempts:

3 left

💡 Hint

Common Mistakes

Using wrong variable names for token or sequence.

Subtracting scores instead of adding.

Sorting ascending loses best sequences.

We add the predicted token to the sequence, add scores, and sort descending to keep best sequences.