Expand, Rerank, and Retrieve: Query Reranking for Open-Domain Question Answering

Yung-Sung Chuang, Wei Fang, Shang-Wen Li, Wen-tau Yih, James Glass
5/26/2023
cs.CL

No official code found. Best implementation: voidism/EAR (38 stars, last commit 2023-05-30).

Abstract

We propose EAR, a query Expansion And Reranking approach for improving passage retrieval, with the application to open-domain question answering. EAR first applies a query expansion model to generate a diverse set of queries, and then uses a query reranker to select the ones that could lead to better retrieval results. Motivated by the observation that the best query expansion often is not picked by greedy decoding, EAR trains its reranker to predict the rank orders of the gold passages when issuing the expanded queries to a given retriever. By connecting better the query expansion model and retriever, EAR significantly enhances a traditional sparse retrieval method, BM25. Empirically, EAR improves top-5/20 accuracy by 3-8 and 5-10 points in in-domain and out-of-domain settings, respectively, when compared to a vanilla query expansion model, GAR, and a dense retrieval model, DPR.

View on arXivView PDF

Code Implementations(1)

voidism/EARCommunity100%

Code for the ACL 2023 long paper - Expand, Rerank, and Retrieve: Query Reranking for Open-Domain Question Answering

382Shell, PythonMay 4, 20233 years ago
bm25dense-retrievalopen-domain-qaquery-expansionquestion-answering+1 more

Similar Papers

Hybrid and Collaborative Passage Reranking

86% match1 repo72023

Beyond Independent Passages: Adaptive Passage Combination Retrieval for Retrieval Augmented Open-Domain Question Answering

84% match2025

CLAP: Coreference-Linked Augmentation for Passage Retrieval

83% match2025

Dense Passage Retrieval for Open-Domain Question Answering

82% match1 repo1.9k2020

Passage-specific Prompt Tuning for Passage Reranking in Question Answering with Large Language Models

82% match1 repo2024

Document Expansion by Query Prediction

82% match1 repo1622019

Cite this paper

@article{chuang2023expand,
  title  = {Expand, Rerank, and Retrieve: Query Reranking for Open-Domain Question Answering},
  author = {Yung-Sung Chuang and Wei Fang and Shang-Wen Li and Wen-tau Yih and James Glass},
  year   = {2023},
  eprint = {2305.17080},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2305.17080v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2305.17080.svg)](https://codeofpaper.com/paper/2305.17080)

Discussion