no code implementations • 1 Jun 2023 • Jonathan Feldstein, Modestas Jurčius, Efthymia Tsamoura
Parallel neurosymbolic architectures have been applied effectively in NLP by distilling knowledge from a logic theory into a deep model. However, prior art faces several limitations including supporting restricted forms of logic theories and relying on the assumption of independence between the logic and the deep network.
1 code implementation • 9 Feb 2023 • Jonathan Feldstein, Dominic Phillips, Efthymia Tsamoura
We present the first principled approach for mining structural motifs in lifted graphical models, languages that blend first-order logic with probabilistic models, which uses a stochastic process to measure the similarity of entities in the data.
no code implementations • 6 Sep 2022 • Davide Buffelli, Efthymia Tsamoura
Our work introduces a regularization technique for injecting symbolic background knowledge into neural SGG models that overcomes the limitations of prior art.
no code implementations • 4 Feb 2021 • Efthymia Tsamoura, David Carral, Enrico Malizia, Jacopo Urbani
The chase is a well-established family of algorithms used to materialize Knowledge Bases (KBs), like Knowledge Graphs (KGs), to tackle important tasks like query answering under dependencies or data cleaning.
no code implementations • 22 Oct 2020 • Efthymia Tsamoura, Loizos Michael
Despite significant progress in the development of neural-symbolic frameworks, the question of how to integrate a neural and a symbolic system in a \emph{compositional} manner remains open.
no code implementations • 18 Nov 2019 • Efthymia Tsamoura, Victor Gutierrez-Basulto, Angelika Kimmig
State-of-the-art inference approaches in probabilistic logic programming typically start by computing the relevant ground program with respect to the queries of interest, and then use this program for probabilistic inference using knowledge compilation and weighted model counting.
no code implementations • 14 Nov 2017 • Michael Benedikt, Boris Motik, Efthymia Tsamoura
We show empirically that our technique can significantly improve the performance of query answering, and that it can mean the difference between answering a query in a few seconds or not being able to process the query at all.