Test legat de ghid · Greu Nivel

Test pentru rezoluția coreferenței

Test mention identity, pronominal anaphora, Winograd reasoning, downstream errors, span ranking, linguistic cues, entity linking, and bias evaluation.

Căi de ghidare aferenteRezoluția coreferenței
Întrebare 1 de 8

When grouping Maria and she in Maria said she was tired, what identity relationship does coreference resolution investigate?

Previzualizează fiecare întrebare8 întrebări

Răspunsurile și explicațiile apar pe măsură ce susțineți testul.

  1. When grouping Maria and she in Maria said she was tired, what identity relationship does coreference resolution investigate?
    • Whether the two mentions refer to the same entity
    • Whether the passage must be translated first
    • Whether both words have the same spelling
    • Whether the sentence has exactly two punctuation marks
  2. Linking a pronoun to an earlier expression for the same referent is a familiar example of which relation?
    • Document-level sentiment classification
    • Segmentarea imaginii
    • Pronominal anaphora
    • Alphabetical token sorting
  3. De ce propoziția „Trofeul nu încapea în valiză pentru că era prea mare” este o carcasă tare clasică (o schemă Winograd)?
    • Conține o greșeală de ortografie
    • Nu are deloc pronume
    • Este scris cu voce pasivă
    • A decide la ce se referă „este” necesită cunoștințe din lumea reală, nu doar gramatică
  4. De ce contează rezoluția coreferinței pentru sarcini precum rezumarea și răspunsul la întrebări?
    • Mărește fontul textului
    • A greși la ce entitate se referă un cuvânt duce la rezultate greșite sau confuze
    • Acesta accelerează hard disk-ul computerului
    • Este util doar pentru poezie
  5. How do influential span-ranking coreference models construct mention links?
    • By requiring all names to be alphabetically adjacent
    • By deleting every pronoun before analyzing identity
    • By scoring candidate mentions and potential earlier antecedents
    • By assigning every span the same database record
  6. Which information can provide cues for a coreference model without guaranteeing a correct link?
    • Mention distance, grammatical agreement, and contextual information
    • Text color alone
    • The speed at which the user typed
    • A requirement that occupation stereotypes determine gender
  7. What extra step distinguishes entity linking from grouping coreferent mentions inside a document?
    • Counting how many pronouns appear without resolving them
    • Associating a mention with a disambiguated external knowledge-base entry
    • Changing every mention to uppercase
    • Requiring every mention to be a different entity
  8. What does WinoBias examine through occupation-based, Winograd-style pronoun examples?
    • The screen resolution used to display occupations
    • A guarantee that every occupation has one gender
    • The file size of every trained model
    • Differences between pro-stereotypical and anti-stereotypical coreference performance