Guide-yakabatana mibvunzo · Pakati Nhanho

ColBERT Kunonoka Kudyidzana Retrieval Quiz

Edza ColBERT tokeni mavekita, yakazvimirira encoding, MaxSim scoring, query-time work, uye mutengo wekuchengetedza wakagadziriswa neColBERTv2 compression.

Nzira dzekutungamira dzinoenderanaColbert Anonoka Kudyidzana Kudzoreredza
Mubvunzo 1 ye 8

ColBERT inomiririra sei mubvunzo kana gwaro?

Tarisa mubvunzo wese8 mibvunzo

Mhinduro uye tsananguro zvinoonekwa paunenge uchitora bvunzo.

  1. ColBERT inomiririra sei mubvunzo kana gwaro?
    • Seimwe avhareji yekumisikidza vector
    • Sezvo mbishi keyword kuverenga chete
    • Sezvo akawanda token-level embedding vectors
    • Semufananidzo
  2. Chii chinonzi scoring function ColBERT inoshandisa inonzi?
    • MaxSim
    • Cosine pooling
    • Softmax cross-entropy
    • Beam search
  3. What query-time work does ColBERT avoid by precomputing document token vectors?
    • All query encoding and all index access
    • Every comparison between a query token and document token
    • The need to store document representations
    • Joint transformer encoding of every query-document pair, while query encoding and similarity search still run
  4. Ko 'kunonoka' mu 'kunonoka kusangana' kunorevei?
    • Iyo modhi inodzidziswa kunonoka mupombi
    • Kudyidzana kuri pakati pemubvunzo nematokeni egwaro kunodzoserwa kune nhanho yezvibodzwa mushure mekuzvimiririra encoding
    • Mibvunzo inosvika pakati pehusiku
    • Zvinyorwa zvinowedzerwa mushure mekutumirwa
  5. Idambudziko ripi nerimwe-vector dense kudzoreredza iro ColBERT inogadzirisa?
    • Inononoka kuita index
    • Haikwanise kumhanya paGPUs
    • Inoda data rakanyorwa pamubvunzo wese
    • Kudzvanya ndima yese muvheta imwe inorasikirwa neruzivo rwakanaka
  6. Chii chakaitwa neColBERTv2 zvakanyanya pane yekutanga?
    • Yakabvisa kudiwa kwechero embeddings
    • Yakachinja kubva kuBERT kuenda kune mutemo-based system
    • Yakawedzera kusarira kudzvanya kudzikisa zvakanyanya saizi ye index
    • Yakabvisa danho reMaxSim
  7. A two-token ColBERT query has best document-token similarities of 0.8 and 0.3. What MaxSim score results?
    • 0.8, retaining only the single largest value across the whole query
    • 1.1, the sum of the two per-query-token maxima
    • 0.55, averaging instead of summing the maxima
    • 0.24, multiplying the two maxima
  8. Why can a ColBERT document index require more storage than a single-vector dense index?
    • It retains multiple token-level representations for each document
    • It never precomputes any document features
    • It must store all transformer gradients for each document
    • It removes every document token before indexing