1 code implementation • 15 May 2023 • Balder ten Cate, Maurice Funk, Jean Christoph Jung, Carsten Lutz
We propose bounded fitting as a scheme for learning description logic concepts in the presence of ontologies.
no code implementations • 22 Aug 2022 • Balder ten Cate, Maurice Funk, Jean Christoph Jung, Carsten Lutz
This note serves three purposes: (i) we provide a self-contained exposition of the fact that conjunctive queries are not efficiently learnable in the Probably-Approximately-Correct (PAC) model, paying clear attention to the complicating fact that this concept class lacks the polynomial-size fitting property, a property that is tacitly assumed in much of the computational learning theory literature; (ii) we establish a strong negative PAC learnability result that applies to many restricted classes of conjunctive queries (CQs), including acyclic CQs for a wide range of notions of "acyclicity"; (iii) we show that CQs (and UCQs) are efficiently PAC learnable with membership queries.
no code implementations • 16 Aug 2020 • Balder ten Cate, Victor Dalmau
We answer the question which conjunctive queries are uniquely characterized by polynomially many positive and negative examples, and how to construct such examples efficiently.
no code implementations • WS 2019 • Karan Singhal, Karthik Raman, Balder ten Cate
There has been significant interest recently in learning multilingual word embeddings -- in which semantically similar words across languages have similar embeddings.
no code implementations • 6 Dec 2014 • Vince Barany, Balder ten Cate, Benny Kimelfeld, Dan Olteanu, Zografoula Vagena
By virtue of extending Datalog, our framework offers a natural integration with the database, and has a robust declarative semantics.
no code implementations • 28 Jan 2013 • Meghyn Bienvenu, Balder ten Cate, Carsten Lutz, Frank Wolter
Ontology-based data access is concerned with querying incomplete data sources in the presence of domain-specific knowledge provided by an ontology.