Home Research Papers Datasets State of the Art Pricing

Discover, visualize, and connect AI research papers. Explore the latest trends and insights in artificial intelligence research.

Product

Home
Research Papers
About

Support

Contact
Terms of Service
Privacy Policy

natural-language-processing-7

Passage Re-Ranking

3260 papers • 126 benchmarks • 313 datasets

Passage re-ranking is the task of scoring and re-ranking a collection of retrieved documents based on an input query.

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in passage-re-ranking-7

Trend

Dataset

Best Model

Actions

MS MARCO

TREC-PM

Libraries

Use these libraries to find passage-re-ranking-7 models and implementations

Datasets

MS MARCO

mMARCO

Subtasks

No subtasks available.

Most implemented papers

Passage Re-ranking with BERT

Kyunghyun Cho, Rodrigo Nogueira•Sat Jan 12 2019

A simple re-implementation of BERT for query-based passage re-ranking 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% in MRR@10.

1264

Content

Introduction Benchmarks Datasets Subtasks Libraries Papers

Paper Graph

Dealing with Typos for BERT-based Passage Retrieval and Ranking

Shengyao Zhuang, G. Zuccon•Thu Aug 26 2021

The Dense Retriever (DR) and BERT re-ranker can become robust to typos in queries, resulting in significantly improved effectiveness compared to models trained without appropriately accounting for typos.

51 0

Paper Graph

Document Expansion by Query Prediction

Kyunghyun Cho, Jimmy J. Lin, Rodrigo Nogueira, Wei Yang•Tue Apr 16 2019

A simple method that predicts which queries will be issued for a given document and then expands it with those predictions with a vanilla sequence-to-sequence model, trained using datasets consisting of pairs of query and relevant documents is proposed.

480 0

Paper Graph

Few-shot Reranking for Multi-hop QA via Language Model Prompting

Lu Wang, Lajanugen Logeswaran, Muhammad Khalifa, Moontae Lee, Ho Hin Lee•Tue May 24 2022

We study few-shot reranking for multi-hop QA (MQA) with open-domain questions. To alleviate the need for a large number of labeled question-document pairs for retriever training, we propose PromptRank, which relies on language model prompting for multi-hop path reranking. PromptRank first constructs an instruction-based prompt that includes a candidate document path and then computes the relevance score between a given question and the path based on the conditional likelihood of the question given the path prompt according to a language model. PromptRank yields strong retrieval performance on HotpotQA with only 128 training examples compared to state-of-the-art methods trained on thousands of examples — 73.6 recall@10 by PromptRank vs. 77.8 by PathRetriever and 77.5 by multi-hop dense retrieval.

25 0

Paper Graph

Mitigating the Position Bias of Transformer Models in Passage Re-Ranking

Sophia Althammer, Sebastian Hofstätter, Markus Zlabinger, A. Hanbury, Aldo Lipani•Sun Jan 17 2021

It is demonstrated that by mitigating the position bias, Transformer-based re-ranking models are equally effective on a biased and debiased dataset, as well as more effective in a transfer-learning setting between two differently biased datasets.

22 0

Paper Graph

An Updated Duet Model for Passage Re-ranking

Nick Craswell, Bhaskar Mitra•Sun Mar 17 2019

Several small modifications to Duet---a deep neural ranking model---and the updated model on the MS MARCO passage ranking task are proposed and significant improvements from the proposed changes based on an ablation study are reported.

54 0

Paper Graph

Set-Encoder: Permutation-Invariant Inter-Passage Attention for Listwise Passage Re-Ranking with Cross-Encoders

Shengyao Zhuang, G. Zuccon, B. Koopman, Benno Stein, Maik Frobe, Harrisen Scells, Ferdinand Schlatt, Martin Potthast, Matthias Hagen•Tue Apr 09 2024

Compared to pointwise models, the Set-Encoder is particularly more effective when considering inter-passage information, such as novelty, and retains its advantageous properties compared to other listwise models.

6 0

Paper Graph

A Modern Perspective on Query Likelihood with Deep Generative Retrieval Models

M. Schedl, Oleg Lesota, Navid Rekabsaz, Carsten Eickhoff, Daniel Cohen, Klaus Antonius Grasserbauer•Thu Jun 24 2021

This work introduces and formalizes the paradigm of deep generative retrieval models defined via the cumulative probabilities of generating query terms, and introduces a novel generative ranker (T-PGN), which combines the encoding capacity of Transformers with the Pointer Generator Network model.

21 0

Paper Graph

Adding a benchmark result helps the community track progress.

Passage Re-Ranking | State-of-the-Art