What deserves the top result?
BM25, RM3 expansion, and QLD plus BGE reranking compete on the ROBUST04 news collection.
Try the method
Interactive explainerHow it works.
Retrieve broadly
Find lexical candidates from 528,030 documents using BM25 or query likelihood.
From the original project.
Saved artifacts · click to inspect
Original artifact ↗
Original artifact ↗
Original artifact ↗
Continue in the source.
Open the source notebook in Jupyter, Colab, or the environment described in the README. Data and model downloads may be required.
git clone https://github.com/eforus-overseer/Text-Retrieval-ROBUST04-Ranking.gitProject artifacts.
notebooks/robust_lambdamart_lgbm.ipynb ↗notebooks/robust_bm25_baseline.ipynb ↗notebooks/robust_qld_crossencoder_v3.ipynb ↗report/report.pdf ↗notebooks/robust_bm25_baseline.py ↗notebooks/robust_neural_reranking_v2.py ↗
Source links point to the original public repository. Credit belongs to the project authors and the dependencies credited there.