natural-language-processing-3

Passage Ranking

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in passage-ranking-3

Trend

Dataset

Best Model

Actions

MS MARCO

Libraries

i

Use these libraries to find passage-ranking-3 models and implementations

Datasets

MS MARCO

Subtasks

No subtasks available.

Most implemented papers

Pseudo-Relevance Feedback for Multiple Representation Dense Retrieval

I. Ounis, Xiao Wang, Craig Macdonald, N. Tonellotto•Sun Jun 20 2021

This work conducts the first study into the potential for multiple representation dense retrieval to be enhanced using pseudo-relevance feedback, and extracts representative feedback embeddings that are shown to both enhance the effectiveness of a reranking as well as an additional dense retrieval operation.

85

Content

0

Paper Graph

RepBERT: Contextualized Text Embeddings for First-Stage Retrieval

Shaoping Ma, Jingtao Zhan, Yiqun Liu, Jiaxin Mao, Min Zhang•Sat Jun 27 2020

This work proposes a different approach, called RepBERT, to represent documents and queries with fixed-length contextualized embeddings, which achieves state-of-the-art results among all initial retrieval techniques.

138 0

Paper Graph

Document Ranking with a Pretrained Sequence-to-Sequence Model

Jimmy J. Lin, Ronak Pradeep, Rodrigo Nogueira, Zhiying Jiang•Fri Mar 13 2020

Surprisingly, it is found that the choice of target tokens impacts effectiveness, even for words that are closely related semantically, which sheds some light on why the sequence-to-sequence formulation for document ranking is effective.

709 0

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

Learning to Rank in Generative Retrieval

Liang Wang, Furu Wei, Wenjie Li, Nan Yang, Yongqing Li•Mon Jun 26 2023

A learning-to-rank framework for generative retrieval, dubbed LTRGR, that enables generative retrieval to learn to rank passages directly, optimizing the autoregressive model toward the final passage ranking target via a rank loss.

68 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

CROWN: Conversational Passage Ranking by Reasoning over Word Networks

Rishiraj Saha Roy, G. Weikum, Magdalena Kaiser•Wed Nov 06 2019

This paper proposes a simple unsupervised method for conversational passage ranking by formulating the passage score for a query as a combination of similarity and coherence, and built a word-proximity network from a large corpus.

1 0

Paper Graph

Learning Contextualized Document Representations for Healthcare Answer Retrieval

Betty van Aken, Felix Alexander Gers, Sebastian Arnold, Alexander Löser, Paul Grundmann•Sun Feb 02 2020

This work shows that the generalized model significantly outperforms several state-of-the-art baselines for healthcare passage ranking and is able to adapt to heterogeneous domains without additional fine-tuning.

15 0

Paper Graph

Conversational Question Answering over Passages by Leveraging Word Proximity Networks

Rishiraj Saha Roy, G. Weikum, Magdalena Kaiser•Sun Apr 26 2020

This work demonstrates CROWN (Conversational passage ranking by Reasoning Over Word Networks): an unsupervised yet effective system for conversational QA with passage responses, that supports several modes of context propagation over multiple turns.

14 0

Paper Graph

Adding a benchmark result helps the community track progress.