English
Related papers

Related papers: Query Embedding Pruning for Dense Retrieval

200 papers

Dense retrieval, which describes the use of contextualised language models such as BERT to identify documents from a collection by leveraging approximate nearest neighbour (ANN) techniques, has been increasing in popularity. Two families of…

Information Retrieval · Computer Science 2021-08-27 Craig Macdonald , Nicola Tonellotto

Pseudo-relevance feedback mechanisms, from Rocchio to the relevance models, have shown the usefulness of expanding and reweighting the users' initial queries using information occurring in an initial set of retrieved documents, known as the…

Information Retrieval · Computer Science 2021-07-02 Xiao Wang , Craig Macdonald , Nicola Tonellotto , Iadh Ounis

With the development of pre-trained language models, the dense retrieval models have become promising alternatives to the traditional retrieval models that rely on exact match and sparse bag-of-words representations. Different from most…

Information Retrieval · Computer Science 2024-03-21 Qi Liu , Gang Guo , Jiaxin Mao , Zhicheng Dou , Ji-Rong Wen , Hao Jiang , Xinyu Zhang , Zhao Cao

In the era of dense retrieval, document indexing and retrieval is largely based on encoding models that transform text documents into embeddings. The efficiency of retrieval is directly proportional to the number of documents and the size…

Information Retrieval · Computer Science 2024-12-16 Federico Siciliano , Francesca Pezzuti , Nicola Tonellotto , Fabrizio Silvestri

Recently, the retrieval models based on dense representations have been gradually applied in the first stage of the document retrieval tasks, showing better performance than traditional sparse vector space models. To obtain high efficiency,…

Information Retrieval · Computer Science 2021-08-20 Hongyin Tang , Xingwu Sun , Beihong Jin , Jingang Wang , Fuzheng Zhang , Wei Wu

Although exact term match between queries and documents is the dominant method to perform first-stage retrieval, we propose a different approach, called RepBERT, to represent documents and queries with fixed-length contextualized…

Information Retrieval · Computer Science 2020-07-21 Jingtao Zhan , Jiaxin Mao , Yiqun Liu , Min Zhang , Shaoping Ma

Information retrieval involves selecting artifacts from a corpus that are most relevant to a given search query. The flavor of retrieval typically used in classical applications can be termed as homogeneous and relaxed, where queries and…

Information Retrieval · Computer Science 2023-10-10 Anirudh Khatry , Yasharth Bajpai , Priyanshu Gupta , Sumit Gulwani , Ashish Tiwari

Dense retrieval techniques employ pre-trained large language models to build a high-dimensional representation of queries and passages. These representations compute the relevance of a passage w.r.t. to a query using efficient similarity…

Information Retrieval · Computer Science 2024-04-04 Franco Maria Nardini , Cosimo Rulli , Rossano Venturini

Ranking has always been one of the top concerns in information retrieval research. For decades, lexical matching signal has dominated the ad-hoc retrieval process, but it also has inherent defects, such as the vocabulary mismatch problem.…

Information Retrieval · Computer Science 2020-10-21 Jingtao Zhan , Jiaxin Mao , Yiqun Liu , Min Zhang , Shaoping Ma

The advent of contextualised language models has brought gains in search effectiveness, not just when applied for re-ranking the output of classical weighting models such as BM25, but also when used directly for passage indexing and…

Information Retrieval · Computer Science 2021-08-20 Craig Macdonald , Nicola Tonellotto , Iadh Ounis

Information retrieval systems have traditionally relied on exact term match methods such as BM25 for first-stage retrieval. However, recent advancements in neural network-based techniques have introduced a new method called dense retrieval.…

Information Retrieval · Computer Science 2025-03-25 Ahmed H. Salamah , Pierre McWhannel , Nicole Yan

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 2024-04-16 Dahlia Shehata

This paper describes a compact and effective model for low-latency passage retrieval in conversational search based on learned dense representations. Prior to our work, the state-of-the-art approach uses a multi-stage pipeline comprising…

Information Retrieval · Computer Science 2021-11-30 Sheng-Chieh Lin , Jheng-Hong Yang , Jimmy Lin

Dense retrieval systems have proven to be effective across various benchmarks, but require substantial memory to store large search indices. Recent advances in embedding compression show that index sizes can be greatly reduced with minimal…

Information Retrieval · Computer Science 2026-01-16 L. Caspari , M. Dinzinger , K. Ghosh Dastidar , C. Fellicious , J. Mitrović , M. Granitzer

Late interaction neural IR models like ColBERT offer a competitive effectiveness-efficiency trade-off across many benchmarks. However, they require a huge memory space to store the contextual representation for all the document tokens. Some…

Information Retrieval · Computer Science 2025-04-18 Yuxuan Zong , Benjamin Piwowarski

While dense retrieval models, which embed queries and documents into a shared low-dimensional space, have gained widespread popularity, they were shown to exhibit important theoretical limitations and considerably lag behind traditional…

Information Retrieval · Computer Science 2026-04-09 Adrian Bracher , Svitlana Vakulenko

Efficient document retrieval heavily relies on the technique of semantic hashing, which learns a binary code for every document and employs Hamming distance to evaluate document distances. However, existing semantic hashing methods are…

Information Retrieval · Computer Science 2022-11-01 Zexuan Qiu , Qinliang Su , Jianxing Yu , Shijing Si

Query Performance Prediction (QPP) estimates the effectiveness of a search engine's results in response to a query without relevance judgments. Traditionally, post-retrieval predictors have focused upon either the distribution of the…

Information Retrieval · Computer Science 2023-10-18 Maria Vlachou , Craig Macdonald

Contrastive learning has been the dominant approach to training dense retrieval models. In this work, we investigate the impact of ranking context - an often overlooked aspect of learning dense retrieval models. In particular, we examine…

Information Retrieval · Computer Science 2023-10-24 George Zerveas , Navid Rekabsaz , Daniel Cohen , Carsten Eickhoff

Dense retrieval, which encodes queries and documents into a single dense vector, has become the dominant neural retrieval approach due to its simplicity and compatibility with fast approximate nearest neighbor algorithms. As the tasks dense…

Information Retrieval · Computer Science 2026-02-06 Julian Killingback , Mahta Rafiee , Madine Manas , Hamed Zamani
‹ Prev 1 2 3 10 Next ›