Skip to content

DanisSharafiev/rl4search

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

6 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

rl4search

Candidate generation consists of BM25 and Semantic search.

There are 3 different realization of the RL algorithms for reranking:

  • Contextual (linear) bandits
  • Neural bandits (plain delta nDCG)
  • Neural bandits (pairloss)

All example code in the test.ipynb

Implemented by:

Danis Sharafiev - - - d.sharafiev@innopolis.university

Almas Bagishaev - - - a.bagishaev@innopolis.university

About

Search engine based on RL techniques for reranking

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors