Related papers: The CTU Prague Relational Learning Repository
Manual digitization of bibliographic metadata is time consuming and labor intensive, especially for historical and real-world archives with highly variable formatting across documents. Despite advances in machine learning, the absence of…
In data lakes, information on the same subject is often fragmented across multiple tables. Table union search aims to find the top-k tables that can be unioned with a query table to extend it with more rows, without relying on metadata or…
Most of the world's data is stored in relational databases. Accessing these requires specialized knowledge of the Structured Query Language (SQL), putting them out of the reach of many people. A recent research thread in Natural Language…
Federated learning is a promising collaborative and privacy-preserving machine learning approach in data-rich smart cities. Nevertheless, the inherent heterogeneity of these urban environments presents a significant challenge in selecting…
This paper provides a technical introduction to the PATSTAT Register database, which contains bibliographical, procedural and legal status data on patent applications handled by the European Patent Office. It presents eight MySQL queries…
Probabilistic relational models provide a well-established formalism to combine first-order logic and probabilistic models, thereby allowing to represent relationships between objects in a relational domain. At the same time, the field of…
Citation intention Classification (CIC) tools classify citations by their intention (e.g., background, motivation) and assist readers in evaluating the contribution of scientific literature. Prior research has shown that pretrained language…
Natural language is hypothetically the best user interface for many domains. However, general models that provide an interface between natural language and any other domain still do not exist. Providing natural language interface to…
We present Thistle, a fully functional vector database. Thistle is an entry into the domain of latent knowledge use in answering search queries, an ongoing research topic at both start-ups and search engine companies. We implement Thistle…
Scientific discovery is increasingly dependent on a scientist's ability to acquire, curate, integrate, analyze, and share large and diverse collections of data. While the details vary from domain to domain, these data often consist of…
The Web today has millions of datasets, and the number of datasets continues to grow at a rapid pace. These datasets are not standalone entities; rather, they are intricately connected through complex relationships. Semantic relationships…
Tabular data is difficult to analyze and to search through, yielding for new tools and interfaces that would allow even non tech-savvy users to gain insights from open datasets without resorting to specialized data analysis tools or even…
A common approach to data analysis involves understanding and manipulating succinct representations of data. In earlier work, we put forward a succinct representation system for relational data called factorised databases and reported on…
Information Extraction is a well-researched area of Natural Language Processing with applications in web search and question answering concerned with identifying entities and relationships between them as expressed in a given context,…
Research data are often released upon journal publication to enable result verification and reproducibility. For that reason, research dissemination infrastructures typically support diverse datasets coming from numerous disciplines, from…
We allow database user to script a parallel relational database engine with a procedural language. Procedural language code is executed as a user defined relational query operator called transducer. Transducer is tightly integrated with…
Relation extraction is used to populate knowledge bases that are important to many applications. Prior datasets used to train relation extraction models either suffer from noisy labels due to distant supervision, are limited to certain…
This paper introduces U-relations, a succinct and purely relational representation system for uncertain databases. U-relations support attribute-level uncertainty using vertical partitioning. If we consider positive relational algebra…
Answering database queries while preserving privacy is an important problem that has attracted considerable research attention in recent years. A canonical approach to this problem is to use synthetic data. That is, we replace the input…
Large language models (LLMs) excel in many natural language processing (NLP) tasks. However, since LLMs can only incorporate new knowledge through training or supervised fine-tuning processes, they are unsuitable for applications that…