Related papers: Dirac Notation, Fock Space and Riemann Metric Tens…
A common approach for knowledge-base entity search is to consider an entity as a document with multiple fields. Models that focus on matching query terms in different fields are popular choices for searching such entity representations. An…
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…
While entity-oriented neural IR models have advanced significantly, they often overlook a key nuance: the varying degrees of influence individual entities within a document have on its overall relevance. Addressing this gap, we present…
In this paper, we demonstrate that information retrieval can be accomplished with a single Transformer, in which all information about the corpus is encoded in the parameters of the model. To this end, we introduce the Differentiable Search…
We introduce and define the novel problem of multi-distribution information retrieval (IR) where given a query, systems need to retrieve passages from within multiple collections, each drawn from a different distribution. Some of these…
Contextual biasing (CB) improves automatic speech recognition for rare and unseen phrases. Recent studies have introduced dynamic vocabulary, which represents context phrases as expandable tokens in autoregressive (AR) models. This method…
Neural ranking models for information retrieval (IR) use shallow or deep neural networks to rank search results in response to a query. Traditional learning to rank models employ machine learning techniques over hand-crafted IR features. By…
Named entities (NE) are objects that are referred to by names such as people, organizations and locations. Named entities and keywords are important to the meaning of a document. We propose a generalized vector space model that combines…
We provide a comparative study between neural word representations and traditional vector spaces based on co-occurrence counts, in a number of compositional tasks. We use three different semantic spaces and implement seven tensor-based…
Vector representations and vector space modeling (VSM) play a central role in modern machine learning. We propose a novel approach to `vector similarity searching' over dense semantic representations of words and documents that can be…
We report a series of experiments with different semantic models on top of various statistical models for extractive text summarization. Though statistical models may better capture word co-occurrences and distribution around the text, they…
In this paper, we investigate mathematical content representations suitable for the automated classification of and the similarity search in STEM documents using standard machine learning algorithms: the Latent Dirichlet Allocation (LDA)…
Text contained in an image carries high-level semantics that can be exploited to achieve richer image understanding. In particular, the mere presence of text provides strong guiding content that should be employed to tackle a diversity of…
Topic modeling based on latent Dirichlet allocation (LDA) has been a framework of choice to deal with multimodal data, such as in image annotation tasks. Another popular approach to model the multimodal data is through deep neural networks,…
The $r$-index represented a breakthrough in compressed indexing of repetitive text collections, outperforming its alternatives by orders of magnitude in query time. Its space usage, $O(r)$ where $r$ is the number of runs in the…
Distributed dense word vectors have been shown to be effective at capturing token-level semantic and syntactic regularities in language, while topic models can form interpretable representations over documents. In this work, we describe…
Named entities have been considered and combined with keywords to enhance information retrieval performance. However, there is not yet a formal and complete model that takes into account entity names, classes, and identifiers together. Our…
Re-ranking utilizes contextual information to optimize the initial ranking list of person or vehicle re-identification (re-ID), which boosts the retrieval performance at post-processing steps. This paper proposes a re-ranking network to…
A challenge of the computer vision community is to understand the semantics of an image, in order to allow image reconstruction based on existing high-level features or to better analyze (semi-)labelled datasets. Towards addressing this…
LiDAR-based place recognition plays a crucial role in Simultaneous Localization and Mapping (SLAM) and LiDAR localization. Despite the emergence of various deep learning-based and hand-crafting-based methods, rotation-induced place…