Skip to content

Latest commit

 

History

1 Commit

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 

Repository files navigation

Controlling Context Granularity and Encoding Local Context for Title Boosted Web Search in ColBERT

Codes for research submitted to Late Interaction Workshop @ ECIR2026. We loaded the stanford-colbert codes (https://github.com/stanford-futuredata/ColBERT) and added scripts used in our analyses and experiments.

  • Analysis
    • stanford-colbert/ColBERT/context_granularity_analysis.ipynb
  • Experiment
    • stanford-colbert/ColBERT/experiment_querytitle_tokenmatch.ipynb
  • Case Study (Index Construction and Search)
    • We modified the stanford-colbert/ColBERT/colbert/modeling/checkpoint.py by adding the docFromText_titlesep method to the ColBERT Checkpoint class

About

No description, website, or topics provided.

Resources

Stars

1 star

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages