Are Quantified Boolean Formulas Hard for Reason-Able Embeddings?

Miniatura

Data

2023

Tytuł czasopisma

ISSN czasopisma

Tytuł tomu

Wydawca

Wydawnictwo Politechniki Łódzkiej
Lodz University of Technology Press

Abstrakt

We aim to establish theoretical boundaries for the applicability of reason-able embeddings, a recently proposed method employing a transferable neural reasoner to shape a latent space of knowledge graph embeddings. Since reason-able embeddings rely on the ALC description logic, we construct a dataset of the hardest concepts in ALC by translating quantified boolean formulas (QBF) from QBFLIB, a benchmark for QBF solvers. We experimentally show the dataset is hard for a symbolic reasoner FaCT++, and analyze the results of reasoning with reason-able embeddings, concluding that the dataset is too hard for them.

Opis

Słowa kluczowe

artificial intelligence, neural-symbolic reasoning, knowledge representation, description logics, sztuczna inteligencja, wnioskowanie neuronalno-symboliczne, reprezentacja wiedzy, logika opisowa

Cytowanie

Potoniec J., Are Quantified Boolean Formulas Hard for Reason-Able Embeddings?. W: Progress in Polish Artificial Intelligence Research 4, Wojciechowski A. (Ed.), Lipiński P. (Ed.)., Seria: Monografie Politechniki Łódzkiej Nr. 2437, Wydawnictwo Politechniki Łódzkiej, Łódź 2023, s. 343-348, ISBN 978-83-66741-92-8, doi: 10.34658/9788366741928.54.

Kolekcje

item.page.endorsement

item.page.review

item.page.supplemented

item.page.referenced