Related papers: Knowledge Discovery Framework for the Virtual Obse…
We propose a novel framework to facilitate the on-demand design of data-centric systems by exploiting domain knowledge from an existing ontology. Its key ingredient is a process that we call focusing, which allows to obtain a schema for a…
We propose V-Doc, a question-answering tool using document images and PDF, mainly for researchers and general non-deep learning experts looking to generate, process, and understand the document visual question answering tasks. The V-Doc…
Research in life sciences is increasingly being conducted in a digital and online environment. In particular, life scientists have been pioneers in embracing new computational tools to conduct their investigations. To support the sharing of…
Real-world information needs require access to structurally diverse knowledge sources, from unstructured text and relational tables to knowledge graphs and property graphs. Existing retrievers, however, operate over one source at a time…
Neurons are the fundamental building blocks of deep neural networks, and their interconnections allow AI to achieve unprecedented results. Motivated by the goal of understanding how neurons encode information, compositional explanations…
Data discovery is crucial for data management and analysis and can benefit from better utilization of metadata. For example, users may want to search data using queries like ``find the tables created by Alex and endorsed by Mike that…
Modern scientific data mainly consist of huge datasets gathered by a very large number of techniques and stored in very diversified and often incompatible data repositories. More in general, in the e-science environment, it is considered as…
The National Academy of Science Astronomy and Astrophysics Survey Committee, in its new Decadal survey entitled Astronomy and Astrophysics in the New Millennium, recommends, as a first priority, the establishment of a National Virtual…
Knowledge-based Vision Question Answering (KB-VQA) systems address complex visual-grounded questions with knowledge retrieved from external knowledge bases. The tasks of knowledge retrieval and answer generation tasks both necessitate…
Astronomy has long had a working network of archives supporting the curation of publications and data. The discipline has already created many of the features which perplex other areas of science: (1) data repositories: (supra)national…
This paper is about a better understanding on the structure and dynamics of science and the usage of these insights for compensating the typical problems that arises in metadata-driven Digital Libraries. Three science model driven retrieval…
Research is an incremental, iterative process, with new results relying and building upon previous ones. Scientists need to find, retrieve, understand, and verify results in order to confidently extend them, even when the results are their…
This paper describes a system to support the visual exploration of Open Data. During his/her interactive experience with the graphics, the user can easily store the current complete state of the visualization application (called a…
Developing a universal model that can efficiently and effectively respond to a wide range of information access requests -- from retrieval to recommendation to question answering -- has been a long-lasting goal in the information retrieval…
We introduce an innovative and mathematically rigorous definition for computing common information from multi-view data, drawing inspiration from G\'acs-K\"orner common information in information theory. Leveraging this definition, we…
The complexity of knowledge production on complex systems is well-known, but there still lacks knowledge framework that would both account for a certain structure of knowledge production at an epistemological level and be directly…
There is a growing need for massive computational resources for the analysis of new astronomical datasets. To tackle this problem, we present here our first steps towards marrying two new and emerging technologies; the Virtual Observatory…
Knowledge-based visual question answering (KB-VQA) requires vision-language models to understand images and use external knowledge, especially for rare entities and long-tail facts. Most existing retrieval-augmented generation (RAG) methods…
Question answering (QA) is a critical task for speech-based retrieval from knowledge sources, by sifting only the answers without requiring to read supporting documents. Specifically, open-domain QA aims to answer user questions on…
The VIALACTEA project has a work package dedicated to Tools and Infrastructure and, inside it, a task for the Database and Virtual Observatory Infrastructure. This task aims at providing an infrastructure to store all the resources needed…