Related papers: Interpreting Dense Retrieval as Mixture of Topics

Diffusion models have demonstrated remarkable performance in generating high-dimensional samples across domains such as vision, language, and the sciences. Although continuous-state diffusion models have been extensively studied both…

Recent advances in open-domain QA have led to strong models based on dense retrieval, but only focused on retrieving textual passages. In this work, we tackle open-domain QA over tables for the first time, and show that retrieval can be…

End-to-end Transformer-based detectors (DETRs) have demonstrated strong detection performance. However, domain generalization (DG) research has primarily focused on convolutional neural network (CNN)-based detectors, while paying little…

Dense retrieval represents queries and documents as high-dimensional embeddings, but these representations can be redundant at the query level: for a given information need, only a subset of dimensions is consistently helpful for ranking.…

We present a new object representation, called Dense RepPoints, that utilizes a large set of points to describe an object at multiple levels, including both box level and pixel level. Techniques are proposed to efficiently process these…

Topics models, such as LDA, are widely used in Natural Language Processing. Making their output interpretable is an important area of research with applications to areas such as the enhancement of exploratory search interfaces and the…

Reproducing results in publications by distributing publicly available source code is becoming ever more popular. Given the difficulty of reproducing machine learning (ML) experiments, there have been significant efforts in reducing the…

Dense captioning is a newly emerging computer vision topic for understanding images with dense language descriptions. The goal is to densely detect visual concepts (e.g., objects, object parts, and interactions between them) from images,…

We study the problem of learning a distribution from samples, when the underlying distribution is a mixture of product distributions over discrete domains. This problem is motivated by several practical applications such as crowd-sourcing,…

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…

Information Retrieval (IR) methods aim to identify documents relevant to a query, which have been widely applied in various natural language tasks. However, existing approaches typically consider only the textual content within documents,…

Dense flow visualization is a popular visualization paradigm. Traditionally, the various models and methods in this area use a continuous formulation, resting upon the solid foundation of functional analysis. In this work, we examine a…

Document-level relation extraction aims to extract relations among entities within a document. Compared with its sentence-level counterpart, Document-level relation extraction requires inference over multiple sentences to extract complex…

Deep learning models for vision tasks are trained on large datasets under the assumption that there exists a universal representation that can be used to make predictions for all samples. Whereas high complexity models are proven to be…

Topic models are a useful analysis tool to uncover the underlying themes within document collections. The dominant approach is to use probabilistic topic models that posit a generative story, but in this paper we propose an alternative way…

With the advancement in technology and the expansion of broadcasting, cross-media retrieval has gained much attention. It plays a significant role in big data applications and consists in searching and finding data from different types of…

Deep neural networks have achieved state-of-the-art results in various vision and/or language tasks. Despite the use of large training datasets, most models are trained by iterating over single input-output pairs, discarding the remaining…

Feature selection of high-dimensional labeled data with limited observations is critical for making powerful predictive modeling accessible, scalable, and interpretable for domain experts. Spectroscopy data, which records the interaction…

Dense retrieval methods have shown great promise over sparse retrieval methods in a range of NLP problems. Among them, dense phrase retrieval-the most fine-grained retrieval unit-is appealing because phrases can be directly used as the…

Neural models learn representations of high-dimensional data on low-dimensional manifolds. Multiple factors, including stochasticities in the training process, model architectures, and additional inductive biases, may induce different…