Guide-yakabatana mibvunzo · Pakati Nhanho

ELMo Contextual Embeddings Quiz

Wongorora kuti ELMo's bidirectional language modhi inogadzira sei mavekita emazwi anoenderana nemamiriro ezvinhu uye anosanganisa akadzokororwa emabasa ekudzika.

Nzira dzekutungamira dzinoenderanaElmo Contextual Embeddings
Mubvunzo 1 ye 8

Ndeupi mutsauko wakakosha pakati peELMo nekutanga embeddings seWord2Vec?

Tarisa mubvunzo wese8 mibvunzo

Mhinduro uye tsananguro zvinoonekwa paunenge uchitora bvunzo.

  1. Ndeupi mutsauko wakakosha pakati peELMo nekutanga embeddings seWord2Vec?
    • ELMo inopa izwi rimwechete mavheji akasiyana zvichienderana nechirevo chechirevo
    • ELMo inoshandisa mavector madiki
    • ELMo inoshanda pamazwi mamwechete, kwete mitsara
    • ELMo haidi data yekudzidziswa
  2. Ndeipi neural architecture inoshandiswa neELMo kuverenga zvinyorwa?
    • A Transformer ine kuzvitarisira
    • Yakadzika bidirectional LSTM mutauro modhi
    • A convolutional image network
    • A simple feedforward network
  3. ELMo inosanganisa sei zvikamu zvayo zvemukati zvebasa rezasi?
    • Inoshandisa chete yekupedzisira yepamusoro
    • Inoenzanisa zvikamu zvose zvakaenzana uye inogadzirisa chigumisiro
    • Inoshandisa yakadzidziswa, basa-rakananga huremu musanganiswa weese matara
    • Inosarudza imwe layer panguva imwe neimwe
  4. Chii chinoshandiswa neELMo sezvikamu zvayo zvekupinza kubata mazwi asingaonekwe?
    • Kutsvaga izwi rose chete
    • MaID eduramazwi akagadziriswa
    • Byte-pair-encoded subwords kubva kuBERT
    • Hunhu hweCNN inomiririra
  5. Zvinenge kuti ELMo yakaunzwa rinhi uye nani?
    • 2018, naAllen Institute yeAI vaongorori
    • 2013, ne Google's Word2Vec timu
    • 2020, na OpenAI
    • 2015, neFacebook AI
  6. Which corpus was used to train the bidirectional language model described in the ELMo paper?
    • The One Billion Word Benchmark
    • The Penn Treebank only
    • A corpus of labeled images
    • The GloVe Common Crawl vectors
  7. What language-model prediction does ELMo's forward LSTM learn?
    • Predicting the previous word from future context
    • Assigning a fixed vector to every document
    • Predicting the next word from the preceding context
    • Predicting a sentence's image resolution
  8. What linguistic information do ELMo's lower and higher LSTM layers tend to capture?
    • Lower layers encode image color, while higher layers encode audio pitch
    • Every layer stores only word frequency and ignores context
    • Higher layers are always limited to punctuation prediction
    • Lower layers tend toward syntax, while higher layers capture more context-dependent semantics