Related papers: Hybrid and Collaborative Passage Reranking

Hybrid and Collaborative Passage Reranking

URL: http://arxiv.org/abs/2305.09313v1
Date: Tue, 16 May 2023 09:38:52 GMT
Title: Hybrid and Collaborative Passage Reranking
Authors: Zongmeng Zhang, Wengang Zhou, Jiaxin Shi, Houqiang Li
Abstract summary: We propose a Hybrid and Collaborative Passage Reranking (HybRank) method. It incorporates the lexical and semantic properties of sparse and dense retrievers for reranking. Built on off-the-shelf retriever features, HybRank is a plug-in reranker capable of enhancing arbitrary passage lists.
Score: 144.83902343298112
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: In passage retrieval system, the initial passage retrieval results may be unsatisfactory, which can be refined by a reranking scheme. Existing solutions to passage reranking focus on enriching the interaction between query and each passage separately, neglecting the context among the top-ranked passages in the initial retrieval list. To tackle this problem, we propose a Hybrid and Collaborative Passage Reranking (HybRank) method, which leverages the substantial similarity measurements of upstream retrievers for passage collaboration and incorporates the lexical and semantic properties of sparse and dense retrievers for reranking. Besides, built on off-the-shelf retriever features, HybRank is a plug-in reranker capable of enhancing arbitrary passage lists including previously reranked ones. Extensive experiments demonstrate the stable improvements of performance over prevalent retrieval and reranking methods, and verify the effectiveness of the core components of HybRank.

Related papers

Improve Dense Passage Retrieval with Entailment Tuning [22.39221206192245]
Key to a retrieval system is to calculate relevance scores to query and passage pairs. We observed that a major class of relevance aligns with the concept of entailment in NLI tasks. We design a method called entailment tuning to improve the embedding of dense retrievers.
arXiv Detail & Related papers (2024-10-21T09:18:30Z)
Meta-prompting Optimized Retrieval-augmented Generation [1.3996171129586734]
Retrieval-augmented generation resorts to content retrieved from external sources in order to leverage the performance of large language models in downstream tasks. We propose a method to refine the retrieved content before it is included in the prompt by resorting to meta-prompting optimization.
arXiv Detail & Related papers (2024-07-04T14:20:12Z)
A Reproducibility Study of PLAID [25.86500025007641]
We compare PLAID with an important baseline missing from the paper: re-ranking a lexical system. We find that applying ColBERTv2 as a re-ranker atop an initial pool of BM25 results provides better efficiency-effectiveness trade-offs in low-latency settings. We find that recently proposed modifications to re-ranking that pull in the neighbors of top-scoring documents overcome this limitation.
arXiv Detail & Related papers (2024-04-23T12:46:53Z)
Modeling Uncertainty and Using Post-fusion as Fallback Improves Retrieval Augmented Generation with LLMs [80.74263278847063]
The integration of retrieved passages and large language models (LLMs) has significantly contributed to improving open-domain question answering. This paper investigates different methods of combining retrieved passages with LLMs to enhance answer generation.
arXiv Detail & Related papers (2023-08-24T05:26:54Z)
How Does Generative Retrieval Scale to Millions of Passages? [68.98628807288972]
We conduct the first empirical study of generative retrieval techniques across various corpus scales. We scale generative retrieval to millions of passages with a corpus of 8.8M passages and evaluating model sizes up to 11B parameters. While generative retrieval is competitive with state-of-the-art dual encoders on small corpora, scaling to millions of passages remains an important and unsolved challenge.
arXiv Detail & Related papers (2023-05-19T17:33:38Z)
HYRR: Hybrid Infused Reranking for Passage Retrieval [18.537666294601458]
Hybrid Infused Reranking for Passages Retrieval is a framework for training rerankers based on a hybrid of BM25 and neural retrieval models. We present evaluations on a supervised passage retrieval task using MS MARCO and zero-shot retrieval tasks using BEIR.
arXiv Detail & Related papers (2022-12-20T18:44:21Z)
Retrieval Augmentation for Commonsense Reasoning: A Unified Approach [64.63071051375289]
We propose a unified framework of retrieval-augmented commonsense reasoning (called RACo) Our proposed RACo can significantly outperform other knowledge-enhanced method counterparts.
arXiv Detail & Related papers (2022-10-23T23:49:08Z)
RocketQAv2: A Joint Training Method for Dense Passage Retrieval and Passage Re-ranking [89.82301733609279]
We propose a novel joint training approach for dense passage retrieval and passage re-ranking. A major contribution is that we introduce the dynamic listwise distillation, where we design a unified listwise training approach for both the retriever and the re-ranker. During the dynamic distillation, the retriever and the re-ranker can be adaptively improved according to each other's relevance information.
arXiv Detail & Related papers (2021-10-14T13:52:55Z)
Joint Passage Ranking for Diverse Multi-Answer Retrieval [56.43443577137929]
We study multi-answer retrieval, an under-explored problem that requires retrieving passages to cover multiple distinct answers for a question. This task requires joint modeling of retrieved passages, as models should not repeatedly retrieve passages containing the same answer at the cost of missing a different valid answer. In this paper, we introduce JPR, a joint passage retrieval model focusing on reranking. To model the joint probability of the retrieved passages, JPR makes use of an autoregressive reranker that selects a sequence of passages, equipped with novel training and decoding algorithms.
arXiv Detail & Related papers (2021-04-17T04:48:36Z)

This list is automatically generated from the titles and abstracts of the papers in this site.