Dense Passage Retrieval Quiz

Mhinduro uye tsananguro zvinoonekwa paunenge uchitora bvunzo.

1. How does Dense Passage Retrieval decide which passages match a query?
   • Kuenzanisa dense vector inomiririra yemibvunzo uye ndima nekufanana
   • Kuverenga kuti mangani mazwi emibvunzo anobuda mugwaro rega rega
   • Kushandura mubvunzo muSQL usati watsvaga
   • Rongedza magwaro zvichienderana nekuburitswa kwaakaitwa nguva pfupi yadarika
2. DPR inoshandisa 'bi-encoder' dhizaini. Zvinorevei izvo?
   • Inonyora zvinyorwa kaviri uye inoita mavhareji emigumisiro
   • Inoshanda chete pamagwaro emitauro miviri
   • Inoisa kodhi mavara uye mazwi panguva imwe chete
   • Inoshandisa encoder maviri akaparadzana, imwe yemibvunzo uye imwe yendima
3. Sei mavheji anogona kuverengerwa pachine nguva muDPR?
   • Nekuti ndima hadzimbochinji kana dzangonyorwa
   • Nekuti iyo query encoder yakadzimwa panguva yekutsvaga
   • Nekuti ndima yega yega yakavharwa yakazvimiririra pane chero mubvunzo
   • Nekuti ndima dzinochengetwa semavara manyoro chete
4. Ndeapi manomano ekudzidzisa anoita kuti DPR iburitse mienzaniso yakawanda yakaipa zvakachipa?
   • Random label flipping
   • In-batch negatives, uchishandisa dzimwe ndima mubatch imwechete
   • Kudonhedza kunze hafu neuroni
   • Kunyora nemaoko ndima yese isiriyo
5. For what vocabulary mismatch can learned DPR representations be useful compared with lexical matching alone?
   • The passage is unrelated but repeats the query's terms
   • Every query contains only an exact serial number
   • The encoder is guaranteed to retrieve the right answer for all inputs
   • A relevant passage expresses a query's idea using different words
6. Ndechipi chishandiso chinowanzoshandiswa kuita DPR yepedyo-muvakidzani kutsvaga nekukurumidza pachiyero?
   • Indekisi yepedyo-yemuvakidzani senge FAISS
   • A spreadsheet sort
   • Injini yekutaura nguva dzose
   • A relationship database join
7. Why can BM25-retrieved nonanswer passages be useful hard negatives when training DPR?
   • They guarantee that every retrieved passage is irrelevant
   • Their lexical overlap can make them challenging distractors that the retriever must distinguish from the answer passage
   • They remove the need for a positive answer passage
   • They force the passage encoder to count words without learning
8. After changing DPR's passage encoder, what should happen to a stored passage-vector index?
   • Keep the old embeddings because encoder weights cannot affect vectors
   • Rename the index without recalculating any representation
   • Recompute the passage embeddings with the intended compatible encoder and update the index
   • Disable the query encoder and search raw filenames instead