Toolkit for domain-specific information retrieval experimentation
-
Updated
May 18, 2026 - Python
Toolkit for domain-specific information retrieval experimentation
A state-of-the-art Information Retrieval system for TREC ROBUST04 achieving MAP 0.3309. Features a Novel 4-Way RRF Fusion architecture combining BM25, Neural Reranking (Cross-Encoders), and LLM-Augmented Query Expansion (Query2Doc) via LiteLLM.
Straightforward SERPs for Lucene indexes
Summarizing my findings on Query Expansion using Generative AI by evaluating and comparing the results of different query expansion methods.
Learning-to-Rank on MS MARCO Passages: candidate generation from prebuilt indexes and re-ranking for QA search
Add a description, image, and links to the pyserini topic page so that developers can more easily learn about it.
To associate your repository with the pyserini topic, visit your repo's landing page and select "manage topics."