English
Related papers

Related papers: BiXSE: Improving Dense Retrieval via Probabilistic…

200 papers

The effective training and evaluation of retrieval systems require a substantial amount of relevance judgments, which are traditionally collected from human assessors -- a process that is both costly and time-consuming. Large Language…

Information Retrieval · Computer Science 2024-12-19 Hossein A. Rahmani , Emine Yilmaz , Nick Craswell , Bhaskar Mitra

Pairing a lexical retriever with a neural re-ranking model has set state-of-the-art performance on large-scale information retrieval datasets. This pipeline covers scenarios like question answering or navigational queries, however, for…

Information Retrieval · Computer Science 2022-10-20 Tim Baumgärtner , Leonardo F. R. Ribeiro , Nils Reimers , Iryna Gurevych

Document expansion (DE) via query generation tackles vocabulary mismatch in sparse retrieval, yet faces limitations: uncontrolled generation producing hallucinated or redundant queries with low diversity; poor generalization from in-domain…

Information Retrieval · Computer Science 2025-10-14 Tzu-Lin Kuo , Wei-Ning Chiu , Wei-Yun Ma , Pu-Jen Cheng

In this paper, we present an approach to learn multilingual sentence embeddings using a bi-directional dual-encoder with additive margin softmax. The embeddings are able to achieve state-of-the-art results on the United Nations (UN)…

Computation and Language · Computer Science 2019-06-18 Yinfei Yang , Gustavo Hernandez Abrego , Steve Yuan , Mandy Guo , Qinlan Shen , Daniel Cer , Yun-hsuan Sung , Brian Strope , Ray Kurzweil

This paper introduces a simple yet effective query expansion approach, denoted as query2doc, to improve both sparse and dense retrieval systems. The proposed method first generates pseudo-documents by few-shot prompting large language…

Information Retrieval · Computer Science 2023-10-12 Liang Wang , Nan Yang , Furu Wei

The training process of ranking models involves two key data selection decisions: a sampling strategy, and a labeling strategy. Modern ranking systems, especially those for performing semantic search, typically use a ``hard negative''…

Information Retrieval · Computer Science 2025-05-28 Andrew Parry , Debasis Ganguly , Sean MacAvaney

Cross-encoders distilled from large language models (LLMs) are often more effective re-rankers than cross-encoders fine-tuned on manually labeled data. However, distilled models do not match the effectiveness of their teacher LLMs. We…

Information retrieval systems are crucial for enabling effective access to large document collections. Recent approaches have leveraged Large Language Models (LLMs) to enhance retrieval performance through query augmentation, but often rely…

Information Retrieval · Computer Science 2025-04-15 Pengcheng Jiang , Jiacheng Lin , Lang Cao , Runchu Tian , SeongKu Kang , Zifeng Wang , Jimeng Sun , Jiawei Han

Neural retrievers based on dense representations combined with Approximate Nearest Neighbors search have recently received a lot of attention, owing their success to distillation and/or better sampling of examples for training -- while…

Information Retrieval · Computer Science 2022-05-13 Thibault Formal , Carlos Lassance , Benjamin Piwowarski , Stéphane Clinchant

Sentence embedding methods have made remarkable progress, yet they still struggle to capture the implicit semantics within sentences. This can be attributed to the inherent limitations of conventional sentence embedding methods that assign…

Computation and Language · Computer Science 2026-01-16 Kohei Oda , Po-Min Chuang , Kiyoaki Shirai , Natthawut Kertkeidkachorn

The scarcity of labeled data in real-world scenarios is a critical bottleneck of deep learning's effectiveness. Semi-supervised semantic segmentation has been a typical solution to achieve a desirable tradeoff between annotation cost and…

Computer Vision and Pattern Recognition · Computer Science 2024-04-30 Kebin Wu , Wenbin Li , Xiaofei Xiao

Conversational search requires accurate interpretation of user intent from complex multi-turn contexts. This paper presents ChatRetriever, which inherits the strong generalization capability of large language models to robustly represent…

Information Retrieval · Computer Science 2024-04-23 Kelong Mao , Chenlong Deng , Haonan Chen , Fengran Mo , Zheng Liu , Tetsuya Sakai , Zhicheng Dou

Computing next-token likelihood ratios between two language models (LMs) is a standard task in training paradigms such as knowledge distillation. Since this requires both models to share the same probability space, it becomes challenging…

Computation and Language · Computer Science 2026-05-07 Buu Phan , Ashish Khisti , Karen Ullrich

Despite the advantages of their low-resource settings, traditional sparse retrievers depend on exact matching approaches between high-dimensional bag-of-words (BoW) representations of both the queries and the collection. As a result,…

Information Retrieval · Computer Science 2022-08-11 Dahlia Shehata , Negar Arabzadeh , Charles L. A. Clarke

Effective sentence embeddings that capture semantic nuances and generalize well across diverse contexts are crucial for natural language processing tasks. We address this challenge by applying SimCSE (Simple Contrastive Learning of Sentence…

Computation and Language · Computer Science 2025-01-24 Yumeng Wang , Ziran Zhou , Junjin Wang

Extreme Multi-label classification (XML) is an important yet challenging machine learning task, that assigns to each instance its most relevant candidate labels from an extremely large label collection, where the numbers of labels, features…

Machine Learning · Computer Science 2019-04-15 Bingyu Wang , Li Chen , Wei Sun , Kechen Qin , Kefeng Li , Hui Zhou

High-dimensional dense embeddings have become central to modern Information Retrieval, but many dimensions are noisy or redundant. Recently proposed DIME (Dimension IMportance Estimation), provides query-dependent scores to identify…

Information Retrieval · Computer Science 2026-04-13 Giulio D'Erasmo , Cesare Campagnano , Antonio Mallia , Pierpaolo Brutti , Nicola Tonellotto , Fabrizio Silvestri

Expansion-enhanced sparse lexical representation improves information retrieval (IR) by minimizing vocabulary mismatch problems during lexical matching. In this paper, we explore the potential of jointly learning dense semantic…

Machine Learning · Computer Science 2024-05-24 Biplob Biswas , Rajiv Ramnath

Recent studies have demonstrated that the ability of dense retrieval models to generalize to target domains with different distributions is limited, which contrasts with the results obtained with interaction-based models. Prior attempts to…

Information Retrieval · Computer Science 2024-03-15 Minghan Li , Eric Gaussier

Relevance labels, which indicate whether a search result is valuable to a searcher, are key to evaluating and optimising search systems. The best way to capture the true preferences of users is to ask them for their careful feedback on…

Information Retrieval · Computer Science 2024-05-20 Paul Thomas , Seth Spielman , Nick Craswell , Bhaskar Mitra
‹ Prev 1 8 9 10 Next ›