Passage Re-ranking with BERT

Rodrigo Nogueira, Kyunghyun Cho
1/13/2019
cs.IRcs.CLcs.LG

Official code: nyu-dl/dl4marco-bert (484 stars, BSD-3-Clause, last commit 2022-01-26).

Abstract

Recently, neural models pretrained on a language modeling task, such as ELMo (Peters et al., 2017), OpenAI GPT (Radford et al., 2018), and BERT (Devlin et al., 2018), have achieved impressive results on various natural language processing tasks such as question-answering and natural language inference. In this paper, we describe a simple re-implementation of BERT for query-based passage re-ranking. Our system is the state of the art on the TREC-CAR dataset and the top entry in the leaderboard of the MS MARCO passage retrieval task, outperforming the previous state of the art by 27% (relative) in MRR@10. The code to reproduce our results is available at https://github.com/nyu-dl/dl4marco-bert

View on arXivView PDF

Code Implementations(1)

nyu-dl/dl4marco-bertOfficial100%
BSD-3-Clause
48488PythonJan 12, 20194 years agoBSD-3-Clause

Similar Papers

Hybrid and Collaborative Passage Reranking

85% match1 repo72023

Rank-K: Test-Time Reasoning for Listwise Reranking

85% match1 repo162025

The Role of Complex NLP in Transformers for Text Ranking?

84% match2022

Re-Ranking Step by Step: Investigating Pre-Filtering for Re-Ranking with Large Language Models

83% match2024

Leveraging Passage Embeddings for Efficient Listwise Reranking with Large Language Models

83% match1 repo512024

TabRank: Chain-of-Thought Distillation for Table Re-Rankers

83% match1 repo12026

Cite this paper

@article{nogueira2019passage,
  title  = {Passage Re-ranking with BERT},
  author = {Rodrigo Nogueira and Kyunghyun Cho},
  year   = {2019},
  eprint = {1901.04085},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1901.04085}
}

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/1901.04085.svg)](https://codeofpaper.com/paper/1901.04085)

Discussion