Retrieving "Deep Learning Models" from the archives

Cross-reference notes under review

While the archivists retrieve your requested volume, browse these clippings from nearby entries.

1. Information Retrieval

   Linked via "Deep learning models"

   Neural Ranking Models
   Deep learning models, particularly those based on transformer architectures (e.g., BERT, T5), treat $\text{IR}$ as a text-pair scoring task. The query and document texts are encoded into dense, fixed-size vectors (embeddings). The model then learns a complex, non-linear function to predict the relevance score. These models excel at understanding context but require massive computational resou…