Are Quantified Boolean Formulas Hard for Reason-Able Embeddings?
Ładowanie...
Data
2023
Autorzy
Tytuł czasopisma
ISSN czasopisma
Tytuł tomu
Wydawca
Wydawnictwo Politechniki Łódzkiej
Lodz University of Technology Press
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.