Passage Re-Ranking
17 papers with code • 2 benchmarks • 2 datasets
Passage re-ranking is the task of scoring and re-ranking a collection of retrieved documents based on an input query.
MS MARCO
mMARCO
Latest papers
Set-Encoder: Permutation-Invariant Inter-Passage Attention for Listwise Passage Re-Ranking with Cross-Encoders
Cross-encoders are effective passage re-rankers.
Multi-Granularity Guided Fusion-in-Decoder
eunseongc/mgfid
•
•
In Open-domain Question Answering (ODQA), it is essential to discern relevant contexts as evidence and avoid spurious ones among retrieved results.
Adapting Language Models to Compress Contexts
princeton-nlp/autocompressors
•
•
Transformer-based language models (LMs) are powerful and widely-applicable tools, but their usefulness is constrained by a finite context window and the expensive computational cost of processing long text documents.
Improving Conversational Passage Re-ranking with View Ensemble
This paper presents ConvRerank, a conversational passage re-ranker that employs a newly developed pseudo-labeling approach.
T2Ranking: A large-scale Chinese Benchmark for Passage Ranking
thuir/t2ranking
•
•
T2Ranking comprises more than 300K queries and over 2M unique passages from real-world search engines.
Few-shot Reranking for Multi-hop QA via Language Model Prompting
To alleviate the need for a large number of labeled question-document pairs for retriever training, we propose PromptRank, which relies on large language models prompting for multi-hop path reranking.
HLATR: Enhance Multi-stage Text Retrieval with Hybrid List Aware Transformer Reranking
Existing text retrieval systems with state-of-the-art performance usually adopt a retrieve-then-reranking architecture due to the high computational cost of pre-trained language models and the large corpus size.
RocketQAv2: A Joint Training Method for Dense Passage Retrieval and Passage Re-ranking
paddlepaddle/rocketqa
•
•
EMNLP 2021
In this paper, we propose a novel joint training approach for dense passage retrieval and passage re-ranking.
Dealing with Typos for BERT-based Passage Retrieval and Ranking
ielab/characterbert-dr
•
•
EMNLP 2021
Our experimental results on the MS MARCO passage ranking dataset show that, with our proposed typos-aware training, 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.
Fast Passage Re-ranking with Contextualized Exact Term Matching and Efficient Passage Expansion
ielab/tilde
•
•
BERT-based information retrieval models are expensive, in both time (query latency) and computational resources (energy, hardware cost), making many of these models impractical especially under resource constraints.
