rpatil524 / txtai / 22147478797

100%

push

github

Add log-odds conjunction fusion for BB25 hybrid search (#1041)

* Add log-odds conjunction fusion for BB25 hybrid search

BB25 normalization outputs calibrated probabilities, but the existing
hybrid fusion uses convex combination which discards the Bayesian
probability semantics. This causes BB25 to regress on 4/5 BEIR datasets.

Add log-odds conjunction fusion (from "From Bayesian Inference to Neural
Computation") that correctly combines probability signals in logit space
with per-query dynamic calibration for dense cosine scores.

- scoring/normalize.py: Extract Bayesian method check into isbayes()
- scoring/base.py: Add default isbayes() returning False
- scoring/tfidf.py: Add isbayes() delegating to normalizer
- search/base.py: Add logodds(), convex(), rrf() fusion methods;
  dispatch based on isbayes()

BEIR nDCG@10 results (BB25+LogOdds vs Default):
  arguana +2.23, fiqa +2.03, scidocs +0.62, scifact +1.33, nfcorpus -1.96

* Extract Hybrid class for score fusion strategies

Move logodds, convex, and rrf fusion methods from Search into
a dedicated Hybrid class, following the same pattern as Normalize.

* Fix coding convention issues in Hybrid class for CI

- Fix black formatting: remove unnecessary parentheses, remove spaces around **
- Fix pylint too-many-branches: extract calibrate() method from logodds()
- Fix pylint unused-variable: rename score to _ in rrf()

39 of 80 new or added lines in 6 files covered. (48.75%)

9510 of 9551 relevant lines covered (99.57%)

1.0 hits per line