Improving Zero-Shot Ranking With Vespa Hybrid Search

rw-book-cover

Metadata

Highlights

  • Pre-trained neural language models, such as BERT, fine-tuned for text ranking, have demonstrated remarkable effectiveness compared to baseline text ranking methods when evaluating the models in-domain. (View Highlight)
  • Information retrieval (IR) evaluation is the process of measuring the effectiveness of an information retrieval system (View Highlight)
  • standard IR metrics such as nDCG@10, Precision@10, and Recall@100. (View Highlight)