Machine Translation and More XLFG

• the third modifier of the mother node

• the number 3 appears in the mother node

• the number of the third child node

• the third element of a set

• the subject is second person singular

• the number of the second child is equal to that of the SUBJ of the mother

• the SUBJ is the second child of the mother

• the mother has two children

• element of the vocabulary

• part of the mother node

• part of the grammar

• element of a (modifier) set

What does the following expression mean? S → NP VP

• the sentence node generates a noun phrase and a verb phrase

• the sentence node has the children NP and then VP

• the sentence node generates exactly one noun and one verb

• the sentence node has the children VP and then NP

Which one is not a (syntactically) correct lexicon entry?

• cookies N[PRED:'cookie', NUMBER:pl, PERSON:3]

• crumbles V[PRED:'crumble', NUMBER:sg, PERSON:4]

• cookies N[PRED:cookies, NUMBER:pl, PERSON:3]

• crumbles V[PRED:'crumble', NUMBER: sg, PERSON:3]

What are the commonly used MT approaches?

• Neural MT

• Human Translation

• Statistical MT

• Rule-based MT

With what metric are translation systems often evaluated?

• VERT

• GRIS

• BLEU

• ROSE

How can the BLEU score be calculated?

• sentence length

• n-gram counts (/comparisons)

• word frequency

• PROPN counts (/comparisons)

Translation errors are more easily traced back to their root in …

• Neural MT systems.

• Statistical MT systems.

• Flawless systems.

• Rule-based MT systems.