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.
Benchmarks
These leaderboards are used to track progress in Passage Retrieval
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find Passage Retrieval models and implementations
Natural Questions
MS MARCO
BEIR
EntityQuestions
QAMPARI
PeerQA
CoreSearch
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
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
•
•
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
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
•
•
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
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
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.
