Related papers: Efficient Neural Ranking using Forward Indexes and…

The Hypencoder, proposed by Killingback et al., is a retrieval framework that replaces the fixed inner-product scoring function used in standard bi-encoders with a query-specific neural network (the $q$-net), whose weights are generated by…

Wilderness search and rescue operations are often carried out over vast landscapes. The search efforts, however, must be undertaken in minimum time to maximize the chance of survival of the victim. Whilst the advent of cheap multicopters in…

Deep learning often faces the challenge of efficiently processing dynamic inputs, such as sensor data or user inputs. For example, an AI writing assistant is required to update its suggestions in real time as a document is edited.…

Deep neural networks (DNN) have demonstrated effectiveness for various applications such as image processing, video segmentation, and speech recognition. Running state-of-the-art DNNs on current systems mostly relies on either…

Recent progress in deep learning-based models has improved photo-realistic (or perceptual) single-image super-resolution significantly. However, despite their powerful performance, many methods are difficult to apply to real-world…

In this paper, we propose to boost low-resource cross-lingual document retrieval performance with deep bilingual query-document representations. We match queries and documents in both source and target languages with four components, each…

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,…

Deep Learning has revolutionized the fields of computer vision, natural language understanding, speech recognition, information retrieval and more. However, with the progressive improvements in deep learning models, their number of…

Neural networks trained with backpropagation often struggle to identify classes that have been observed a small number of times. In applications where most class labels are rare, such as language modelling, this can become a performance…

Visual document retrieval has become essential for accessing information in visually rich documents. Existing approaches fall into two camps. Late-interaction retrievers achieve strong quality through fine-grained token-level matching but…

Reranking is a critical stage in contemporary information retrieval (IR) systems, improving the relevance of the user-presented final results by honing initial candidate sets. This paper is a thorough guide to examine the changing reranker…

Recently, Transformer-based encoder-decoder models have demonstrated strong performance in multilingual speech recognition. However, the decoder's autoregressive nature and large size introduce significant bottlenecks during inference.…

Neural information retrieval systems typically use a cascading pipeline, in which a first-stage model retrieves a candidate set of documents and one or more subsequent stages re-rank this set using contextualized language models such as…

Both performance and efficiency are important to semantic segmentation. State-of-the-art semantic segmentation algorithms are mostly based on dilated Fully Convolutional Networks (dilatedFCN), which adopt dilated convolutions in the…

Similar question retrieval is a core task in community-based question answering (CQA) services. To balance the effectiveness and efficiency, the question retrieval system is typically implemented as multi-stage rankers: The first-stage…

Learned multivector representations power modern search systems with strong retrieval effectiveness, but their real-world use is limited by the high cost of exhaustive token-level retrieval. Therefore, most systems adopt a…

Classical information retrieval (IR) methods, such as query likelihood and BM25, score documents independently w.r.t. each query term, and then accumulate the scores. Assuming query term independence allows precomputing term-document scores…

Large Reasoning Models (LRMs) have demonstrated impressive capabilities but suffer from cognitive inefficiencies like "overthinking" simple problems and "underthinking" complex ones. While existing methods that use supervised fine-tuning…

Recurrent neural networks are effective models to process sequences. However, they are unable to learn long-term dependencies because of their inherent sequential nature. As a solution, Vaswani et al. introduced the Transformer, a model…

Filtered ANN search is an increasingly important problem in vector retrieval, yet systems face a difficult trade-off due to the execution order: Pre-filtering (filtering first, then ANN over the passing subset) requires expensive…