Machine Translation Flashcards

Which decoding strategy in neural MT generates the most probable translation by greedily selecting the highest-probability token at each step?

Answer: Greedy decoding

Greedy decoding selects the single highest-probability token at each step without exploring alternatives.

What does the BLEU score primarily measure in machine translation evaluation?

Answer: N-gram precision of the translation against reference(s)

BLEU measures n-gram precision of the MT output against one or more human reference translations.

In the transformer encoder-decoder architecture for MT, what is the role of cross-attention?

Answer: Allows the decoder to attend to encoder outputs

Cross-attention in the decoder lets each target position attend over all encoder hidden states to gather source context.

Which phenomenon occurs when an NMT model repeatedly generates the same phrase or omits parts of the source sentence?

Answer: Over-translation and under-translation

Over-translation (repeated content) and under-translation (omitted content) are common NMT failure modes caused by imperfect attention alignment.

What is 'back-translation' used for in low-resource neural machine translation?

Answer: Generating synthetic source sentences from target monolingual data

Back-translation uses a reverse MT system to translate target-language monolingual text into the source, creating synthetic parallel data for training.

Which metric penalizes MT output that is shorter than the reference translation?

Answer: BLEU (brevity penalty)

BLEU includes a brevity penalty that reduces the score when the hypothesis is shorter than the reference.

In statistical machine translation, what does an 'alignment model' estimate?

Answer: The correspondence between source and target words

An alignment model (e.g., IBM Models) estimates the probability that source word i generated target word j.