Related papers: The Potential of Learned Index Structures for Inde…
Deep learning is computationally intensive, with significant efforts focused on reducing arithmetic complexity, particularly regarding energy consumption dominated by data movement. While existing literature emphasizes inference, training…
Numerous embedding models have been recently explored to incorporate semantic knowledge into visual recognition. Existing methods typically focus on minimizing the distance between the corresponding images and texts in the embedding space…
Recent work proposed learned index structures, which learn the distribution of the underlying dataset to improve performance. The initial work on learned indexes has shown that by learning the cumulative distribution function of the data,…
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…
Configuring databases for efficient querying is a complex task, often carried out by a database administrator. Solving the problem of building indexes that truly optimize database access requires a substantial amount of database and domain…
Word embeddings -- distributed representations of words -- in deep learning are beneficial for many tasks in natural language processing (NLP). However, different embedding sets vary greatly in quality and characteristics of the captured…
In information retrieval, learning to rank constructs a machine-based ranking model which given a query, sorts the search results by their degree of relevance or importance to the query. Neural networks have been successfully applied to…
In this work, we evaluate contrastive models for the task of image retrieval. We hypothesise that models that are learned to encode semantic similarity among instances via discriminative learning should perform well on the task of image…
Most text-based information retrieval (IR) systems index objects by words or phrases. These discrete systems have been augmented by models that use embeddings to measure similarity in continuous space. But continuous-space models are…
Representing sorted integer sequences in small space is a central problem for large-scale retrieval systems such as Web search engines. Efficient query resolution, e.g., intersection or random access, is achieved by carefully partitioning…
The Burrows-Wheeler Transform is a string transformation that plays a fundamental role for the design of self-indexing compressed data structures. Over the years, researchers have successfully extended this transformation outside the…
Large Language Models (LLMs) are increasingly expected to operate over long contexts, yet standard softmax attention incurs a KV cache that grows linearly with sequence length, quickly becoming the bottleneck for long context inference. A…
Neural networks with deep architectures have demonstrated significant performance improvements in computer vision, speech recognition, and natural language processing. The challenges in information retrieval (IR), however, are different…
Persistence diagrams have been widely recognized as a compact descriptor for characterizing multiscale topological features in data. When many datasets are available, statistical features embedded in those persistence diagrams can be…
Recently, a new paradigm called Differentiable Search Index (DSI) has been proposed for document retrieval, wherein a sequence-to-sequence model is learned to directly map queries to relevant document identifiers. The key idea behind DSI is…
Recognizing shallow linguistic patterns, such as basic syntactic relationships between words, is a common task in applied natural language and text processing. The common practice for approaching this task is by tedious manual definition of…
We present a method for feature interpretation that makes use of recent advances in autoregressive density estimation models to invert model representations. We train generative inversion models to express a distribution over input features…
The run-length compressed Burrows-Wheeler transform (RLBWT) used in conjunction with the backward search introduced in the FM index is the centerpiece of most compressed indexes working on highly-repetitive data sets like biological…
Users issue queries to Search Engines, and try to find the desired information in the results produced. They repeat this process if their information need is not met at the first place. It is crucial to identify the important words in a…
This paper presents a novel method for efficient image retrieval, based on a simple and effective hashing of CNN features and the use of an indexing structure based on Bloom filters. These filters are used as gatekeepers for the database of…