Passage Retrieval

111 papers with code • 4 benchmarks • 8 datasets

Passage retrieval is a specialized type of IR application that retrieves relevant passages (or pieces of text) rather than an entire ranked set of documents.


Use these libraries to find Passage Retrieval models and implementations

Most implemented papers

Dense Passage Retrieval for Open-Domain Question Answering

facebookresearch/DPR EMNLP 2020

Open-domain question answering relies on efficient passage retrieval to select candidate contexts, where traditional sparse vector space models, such as TF-IDF or BM25, are the de facto method.

Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering

princeton-nlp/DensePhrases EACL 2021

Generative models for open domain question answering have proven to be competitive, without resorting to external knowledge.

Passage Re-ranking with BERT

nyu-dl/dl4marco-bert 13 Jan 2019

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.

Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval

microsoft/ANCE ICLR 2021

In this paper, we identify that the main bottleneck is in the training mechanisms, where the negative instances used in training are not representative of the irrelevant documents in testing.

ZusammenQA: Data Augmentation with Specialized Models for Cross-lingual Open-retrieval Question Answering System

umanlp/zusammenqa NAACL (MIA) 2022

This paper introduces our proposed system for the MIA Shared Task on Cross-lingual Open-retrieval Question Answering (COQA).

Context-Aware Sentence/Passage Term Importance Estimation For First Stage Retrieval

AdeDZY/DeepCT 23 Oct 2019

When applied to passages, DeepCT-Index produces term weights that can be stored in an ordinary inverted index for passage retrieval.

Overview of the TREC 2019 deep learning track

bmitra-msft/TREC-Deep-Learning-Quick-Start 17 Mar 2020

The Deep Learning Track is a new track for TREC 2019, with the goal of studying ad hoc ranking in a large data regime.

Open-Domain Question Answering Goes Conversational via Question Rewriting

apple/ml-qrecc NAACL 2021

We introduce a new dataset for Question Rewriting in Conversational Context (QReCC), which contains 14K conversations with 80K question-answer pairs.

Learning To Retrieve: How to Train a Dense Retrieval Model Effectively and Efficiently

jingtaozhan/DRhard 20 Oct 2020

Through this process, it teaches the DR model how to retrieve relevant documents from the entire corpus instead of how to rerank a potentially biased sample of documents.

BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models

UKPLab/beir 17 Apr 2021

To address this, and to facilitate researchers to broadly evaluate the effectiveness of their models, we introduce Benchmarking-IR (BEIR), a robust and heterogeneous evaluation benchmark for information retrieval.