CoRT: Complementary Rankings from Transformers

• URL: http://arxiv.org/abs/2010.10252v2
• Date: Tue, 25 May 2021 13:15:31 GMT
• Title: CoRT: Complementary Rankings from Transformers
• Authors: Marco Wrzalik and Dirk Krechel
• Abstract summary: CoRT is a simple neural first-stage ranking model that leverages contextual representations from pretrained language models. We show that CoRT significantly increases the candidate recall by complementing BM25 with missing candidates. We further demonstrate that passage retrieval using CoRT can be realized with surprisingly low latencies.
• Score: 8.37609145576126
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Many recent approaches towards neural information retrieval mitigate their computational costs by using a multi-stage ranking pipeline. In the first stage, a number of potentially relevant candidates are retrieved using an efficient retrieval model such as BM25. Although BM25 has proven decent performance as a first-stage ranker, it tends to miss relevant passages. In this context we propose CoRT, a simple neural first-stage ranking model that leverages contextual representations from pretrained language models such as BERT to complement term-based ranking functions while causing no significant delay at query time. Using the MS MARCO dataset, we show that CoRT significantly increases the candidate recall by complementing BM25 with missing candidates. Consequently, we find subsequent re-rankers achieve superior results with less candidates. We further demonstrate that passage retrieval using CoRT can be realized with surprisingly low latencies.

Related papers

• Deep Retrieval at CheckThat! 2025: Identifying Scientific Papers from Implicit Social Media Mentions via Hybrid Retrieval and Re-Ranking [4.275139302875217]
  We present the methodology and results of the Deep Retrieval team for subtask 4b of the CLEF CheckThat! 2025 competition.<n>We propose a hybrid retrieval pipeline that combines lexical precision, semantic generalization, and deep contextual re-ranking.<n>Our approach achieves a mean reciprocal rank at 5 (MRR@5) of 76.46% on the development set and 66.43% on the hidden test set.
  arXiv  Detail & Related papers  (2025-05-29T08:55:39Z)
• Inference Scaling for Bridging Retrieval and Augmented Generation [47.091086803980765]
  Retrieval-augmented generation (RAG) has emerged as a popular approach to steering the output of a large language model (LLM) We show such bias can be mitigated, from inference scaling, aggregating inference calls from the permuted order of retrieved contexts. We showcase the effectiveness of MOI on diverse RAG tasks, improving ROUGE-L on MS MARCO and EM on HotpotQA benchmarks by 7 points.
  arXiv  Detail & Related papers  (2024-12-14T05:06:43Z)
• An Early FIRST Reproduction and Improvements to Single-Token Decoding for Fast Listwise Reranking [50.81324768683995]
  FIRST is a novel approach that integrates a learning-to-rank objective and leveraging the logits of only the first generated token. We extend the evaluation of FIRST to the TREC Deep Learning datasets (DL19-22), validating its robustness across diverse domains. Our experiments confirm that fast reranking with single-token logits does not compromise out-of-domain reranking quality.
  arXiv  Detail & Related papers  (2024-11-08T12:08:17Z)
• FIRST: Faster Improved Listwise Reranking with Single Token Decoding [56.727761901751194]
  First, we introduce FIRST, a novel listwise LLM reranking approach leveraging the output logits of the first generated identifier to directly obtain a ranked ordering of the candidates. Empirical results demonstrate that FIRST accelerates inference by 50% while maintaining a robust ranking performance with gains across the BEIR benchmark. Our results show that LLM rerankers can provide a stronger distillation signal compared to cross-encoders, yielding substantial improvements in retriever recall after relevance feedback.
  arXiv  Detail & Related papers  (2024-06-21T21:27:50Z)
• Generative Relevance Feedback and Convergence of Adaptive Re-Ranking: University of Glasgow Terrier Team at TREC DL 2023 [20.95345024616033]
  This paper describes our participation in the TREC 2023 Deep Learning Track. We submitted runs that apply generative relevance feedback from a large language model in both a zero-shot and pseudo-relevance feedback setting. We find some performance gains from the application of generative query reformulation.
  arXiv  Detail & Related papers  (2024-05-02T09:36:00Z)
• Efficient Inverted Indexes for Approximate Retrieval over Learned Sparse Representations [8.796275989527054]
  We propose a novel organization of the inverted index that enables fast retrieval over learned sparse embeddings. Our approach organizes inverted lists into geometrically-cohesive blocks, each equipped with a summary vector. Our results indicate that Seismic is one to two orders of magnitude faster than state-of-the-art inverted index-based solutions.
  arXiv  Detail & Related papers  (2024-04-29T15:49:27Z)
• Sequencing Matters: A Generate-Retrieve-Generate Model for Building Conversational Agents [9.191944519634111]
  The Georgetown InfoSense group has done in regard to solving the challenges presented by TREC iKAT 2023. Our submitted runs outperform the median runs by a significant margin, exhibiting superior performance in nDCG across various cut numbers and in overall success rate. Our solution involves the use of Large Language Models (LLMs) for initial answers, answer grounding by BM25, passage quality filtering by logistic regression, and answer generation by LLMs again.
  arXiv  Detail & Related papers  (2023-11-16T02:37:58Z)
• Unsupervised Dense Retrieval with Relevance-Aware Contrastive Pre-Training [81.3781338418574]
  We propose relevance-aware contrastive learning. We consistently improve the SOTA unsupervised Contriever model on the BEIR and open-domain QA retrieval benchmarks. Our method can not only beat BM25 after further pre-training on the target corpus but also serves as a good few-shot learner.
  arXiv  Detail & Related papers  (2023-06-05T18:20:27Z)
• Provably Convergent Subgraph-wise Sampling for Fast GNN Training [122.68566970275683]
  We propose a novel subgraph-wise sampling method with a convergence guarantee, namely Local Message Compensation (LMC) LMC retrieves the discarded messages in backward passes based on a message passing formulation of backward passes. Experiments on large-scale benchmarks demonstrate that LMC is significantly faster than state-of-the-art subgraph-wise sampling methods.
  arXiv  Detail & Related papers  (2023-03-17T05:16:49Z)
• HYRR: Hybrid Infused Reranking for Passage Retrieval [18.537666294601458]
  Hybrid Infused Reranking for Passages Retrieval is a framework for training rerankers based on a hybrid of BM25 and neural retrieval models. We present evaluations on a supervised passage retrieval task using MS MARCO and zero-shot retrieval tasks using BEIR.
  arXiv  Detail & Related papers  (2022-12-20T18:44:21Z)
• Sample-Efficient Optimisation with Probabilistic Transformer Surrogates [66.98962321504085]
  This paper investigates the feasibility of employing state-of-the-art probabilistic transformers in Bayesian optimisation. We observe two drawbacks stemming from their training procedure and loss definition, hindering their direct deployment as proxies in black-box optimisation. We introduce two components: 1) a BO-tailored training prior supporting non-uniformly distributed points, and 2) a novel approximate posterior regulariser trading-off accuracy and input sensitivity to filter favourable stationary points for improved predictive performance.
  arXiv  Detail & Related papers  (2022-05-27T11:13:17Z)
• Towards Unsupervised Dense Information Retrieval with Contrastive Learning [38.42033176712396]
  We show that contrastive learning can be used to train unsupervised dense retrievers. Our model outperforms BM25 on 11 out of 15 datasets.
  arXiv  Detail & Related papers  (2021-12-16T18:57:37Z)
• Pre-training Tasks for Embedding-based Large-scale Retrieval [68.01167604281578]
  We consider the large-scale query-document retrieval problem. Given a query (e.g., a question), return the set of relevant documents from a large document corpus. We show that the key ingredient of learning a strong embedding-based Transformer model is the set of pre-training tasks.
  arXiv  Detail & Related papers  (2020-02-10T16:44:00Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.