Related papers: Semantic Certainty Assessment in Vector Retrieval …

The search of information in large text repositories has been plagued by the so-called document-query vocabulary gap, i.e. the semantic discordance between the contents in the stored document entities on the one hand and the human query on…

The massive increase in the data volume and dataset availability for analysts compels researchers to focus on data content and select high-quality datasets to enhance the performance of analytics operators. While selecting high-quality data…

Vector databases are critical infrastructure in AI systems, and average recall is the dominant metric for their evaluation. Both users and researchers rely on it to choose and optimize their systems. We show that relying on average recall…

Vector databases typically rely on approximate nearest neighbor (ANN) search to retrieve the top-k closest vectors to a query in embedding space. While effective, this approach often yields semantically redundant results, missing the…

Multi-vector embedding models have emerged as a powerful paradigm for document retrieval, preserving fine-grained visual and textual details through token-level representations. However, this expressiveness comes at a staggering cost:…

Classification is a common AI problem, and vector search is a typical solution. This transforms a given body of text into a numerical representation, known as an embedding, and modern improvements to vector search focus on optimising speed…

Formula retrieval is an important topic in Mathematical Information Retrieval. We propose SSEmb, a novel embedding framework capable of capturing both structural and semantic features of mathematical formulas. Structurally, we employ Graph…

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…

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…

A key obstacle in automated analytics and meta-learning is the inability to recognize when different datasets contain measurements of the same variable. Because provided attribute labels are often uninformative in practice, this task may be…

Geometric verification is considered a de facto solution for the re-ranking task in image retrieval. In this study, we propose a novel image retrieval re-ranking network named Correlation Verification Networks (CVNet). Our proposed network,…

Semantic caching enhances the efficiency of large language model (LLM) systems by identifying semantically similar queries, storing responses once, and serving them for subsequent equivalent requests. However, existing semantic caching…

Pre-trained language models have been widely exploited to learn dense representations of documents and queries for information retrieval. While previous efforts have primarily focused on improving effectiveness and user satisfaction,…

Recently, several dense retrieval (DR) models have demonstrated competitive performance to term-based retrieval that are ubiquitous in search systems. In contrast to term-based matching, DR projects queries and documents into a dense vector…

The convolutional neural network (CNN) features can give a good description of image content, which usually represent images with unique global vectors. Although they are compact compared to local descriptors, they still cannot efficiently…

Rapid response, namely low latency, is fundamental in search applications; it is particularly so in interactive search sessions, such as those encountered in conversational settings. An observation with a potential to reduce latency asserts…

Feature selection aims to identify the optimal feature subset for enhancing downstream models. Effective feature selection can remove redundant features, save computational resources, accelerate the model learning process, and improve the…

For a product of interest, we propose a search method to surface a set of reference products. The reference products can be used as candidates to support downstream modeling tasks and business applications. The search method consists of…

Distributional semantics models derive word space from linguistic items in context. Meaning is obtained by defining a distance measure between vectors corresponding to lexical entities. Such vectors present several problems. In this paper…

Traditional retrieval methods rely on transforming user queries into vector representations and retrieving documents based on cosine similarity within an embedding space. While efficient and scalable, this approach often fails to handle…