CLIRDec 20, 2022

HYRR: Hybrid Infused Reranking for Passage Retrieval

arXiv:2212.10528v184 citationsh-index: 26
Originality Incremental advance
AI Analysis

This work addresses passage retrieval for information retrieval systems, presenting an incremental improvement by leveraging hybrid models for more robust reranking.

The paper tackles the problem of improving passage retrieval by proposing HYRR, a framework for training rerankers using a hybrid of BM25 and neural retrieval models, which achieves strong performance on supervised and zero-shot tasks as shown in evaluations on MS MARCO and BEIR.

We present Hybrid Infused Reranking for Passages Retrieval (HYRR), a framework for training rerankers based on a hybrid of BM25 and neural retrieval models. Retrievers based on hybrid models have been shown to outperform both BM25 and neural models alone. Our approach exploits this improved performance when training a reranker, leading to a robust reranking model. The reranker, a cross-attention neural model, is shown to be robust to different first-stage retrieval systems, achieving better performance than rerankers simply trained upon the first-stage retrievers in the multi-stage systems. We present evaluations on a supervised passage retrieval task using MS MARCO and zero-shot retrieval tasks using BEIR. The empirical results show strong performance on both evaluations.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes