Passage Retrieval

130 papers with code • 19 benchmarks • 9 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.

Libraries

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

jhyuklee/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.

Unsupervised Dense Information Retrieval with Contrastive Learning

facebookresearch/contriever 16 Dec 2021

In this work, we explore the limits of contrastive learning as a way to train unsupervised dense retrievers and show that it leads to strong performance in various retrieval settings.

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.

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.

ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction

stanford-futuredata/ColBERT NAACL 2022

Neural information retrieval (IR) has greatly advanced search and other knowledge-intensive language tasks.

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).

DAPR: A Benchmark on Document-Aware Passage Retrieval

ukplab/acl2024-dapr 23 May 2023

This drives us to build a benchmark for this task including multiple datasets from heterogeneous domains.

Drop your Decoder: Pre-training with Bag-of-Word Prediction for Dense Passage Retrieval

ma787639046/bowdpr 20 Jan 2024

In this study, we aim to shed light on this issue by revealing that masked auto-encoder (MAE) pre-training with enhanced decoding significantly improves the term coverage of input tokens in dense representations, compared to vanilla BERT checkpoints.