Beam search decoding in NLP - Cheat Sheet & Quick Revision

Recall & Review

beginner

What is beam search decoding in NLP?

Beam search decoding is a method to find the most likely sequence of words by exploring multiple options at each step, keeping only the best few sequences (called beams) instead of just one.

beginner

Why is beam search better than greedy search?

Beam search keeps multiple candidate sequences at each step, so it can avoid early mistakes that greedy search makes by choosing only the single best option at each step.

intermediate

What does the beam width control in beam search decoding?

Beam width controls how many candidate sequences are kept at each step. A larger beam width means more sequences are considered, which can improve results but takes more time.

intermediate

How does beam search handle sequence probabilities during decoding?

Beam search multiplies or adds the log probabilities of words in a sequence to score each candidate. It keeps the top sequences with the highest total scores at each step.

intermediate

What is a common drawback of beam search decoding?

Beam search can still miss the best sequence if the beam width is too small, and it can be slower than greedy search because it keeps multiple candidates.

What does beam search keep track of during decoding?

A Multiple best candidate sequences

B Only the single best sequence

C Random sequences

D All possible sequences

Beam search keeps multiple best candidate sequences (beams) at each step to explore more options.

What happens if you increase the beam width in beam search?

A The model trains faster

B Fewer sequences are considered, speeding up decoding

C More sequences are considered, improving accuracy but increasing computation

D The output becomes random

Increasing beam width means more candidate sequences are kept, which can improve results but requires more computation.

Which of these is a key difference between greedy search and beam search?

A Beam search ignores probabilities

B Greedy search keeps one best sequence; beam search keeps multiple

C Greedy search is slower than beam search

D Beam search only works for images

Greedy search keeps only the single best sequence at each step, while beam search keeps multiple candidates.

How does beam search score candidate sequences?

A By summing or multiplying word probabilities

B By counting word length

C By random selection

D By alphabetical order

Beam search scores sequences by combining the probabilities of each word, often using log probabilities for numerical stability.

What is a potential downside of using a very small beam width?

A It will always find the best sequence

B It will generate random outputs

C It will be too slow

D It may miss better sequences and behave like greedy search

A small beam width limits the search and can cause the method to miss better sequences, similar to greedy search.

Explain how beam search decoding works and why it is used instead of greedy search.

Think about how exploring more options helps find better sentences.

Describe the trade-offs involved in choosing the beam width for beam search decoding.

Consider speed versus quality of results.