Kuiz berkaitan panduan · Keras Tahap

Kuiz Resolusi Coreference

Identiti sebutan ujian, anafora pronominal, penaakulan Winograd, ralat hiliran, kedudukan rentang, isyarat linguistik, pautan entiti dan penilaian berat sebelah.

Laluan panduan yang berkaitanResolusi Coreference
soalan 1 daripada 8

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

Pratonton setiap soalan8 soalan

Jawapan dan penjelasan muncul semasa anda mengambil kuiz.

  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
    • Pembahagian imej
    • Pronominal anaphora
    • Alphabetical token sorting
  3. Mengapakah ayat "Trofi itu tidak muat dalam beg pakaian kerana terlalu besar" kes keras klasik (skema Winograd)?
    • Ia mengandungi ralat ejaan
    • Ia tidak mempunyai kata ganti sama sekali
    • Ia ditulis dengan suara pasif
    • Memutuskan apa yang "ia" merujuk kepada memerlukan pengetahuan dunia sebenar, bukan hanya tatabahasa
  4. Mengapakah resolusi rujukan penting untuk tugasan seperti ringkasan dan menjawab soalan?
    • Ia menjadikan fon teks lebih besar
    • Tersilap entiti yang dirujuk oleh perkataan membawa kepada output yang salah atau mengelirukan
    • Ia mempercepatkan pemacu keras komputer
    • Ia hanya berguna untuk puisi
  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