Neural Class Expression Synthesis

N.J. KOUAGOU, S. Heindorf, C. Demir, A.-C. Ngonga Ngomo, ArXiv:2111.08486 (2021).

Preprint | English
Department
Abstract
Class expression learning is a branch of explainable supervised machine learning of increasing importance. Most existing approaches for class expression learning in description logics are search algorithms or hard-rule-based. In particular, approaches based on refinement operators suffer from scalability issues as they rely on heuristic functions to explore a large search space for each learning problem. We propose a new family of approaches, which we dub synthesis approaches. Instances of this family compute class expressions directly from the examples provided. Consequently, they are not subject to the runtime limitations of search-based approaches nor the lack of flexibility of hard-rule-based approaches. We study three instances of this novel family of approaches that use lightweight neural network architectures to synthesize class expressions from sets of positive examples. The results of their evaluation on four benchmark datasets suggest that they can effectively synthesize high-quality class expressions with respect to the input examples in under a second on average. Moreover, a comparison with the state-of-the-art approaches CELOE and ELTL suggests that we achieve significantly better F-measures on large ontologies. For reproducibility purposes, we provide our implementation as well as pre-trained models in the public GitHub repository at https://github.com/ConceptLengthLearner/NCES
Publishing Year
Journal Title
arXiv:2111.08486
LibreCat-ID

Cite this

KOUAGOU NJ, Heindorf S, Demir C, Ngonga Ngomo A-C. Neural Class Expression Synthesis. arXiv:211108486. Published online 2021.
KOUAGOU, N. J., Heindorf, S., Demir, C., & Ngonga Ngomo, A.-C. (2021). Neural Class Expression Synthesis. In arXiv:2111.08486.
@article{KOUAGOU_Heindorf_Demir_Ngonga Ngomo_2021, title={Neural Class Expression Synthesis}, journal={arXiv:2111.08486}, author={KOUAGOU, N’Dah Jean and Heindorf, Stefan and Demir, Caglar and Ngonga Ngomo, Axel-Cyrille}, year={2021} }
KOUAGOU, N’Dah Jean, Stefan Heindorf, Caglar Demir, and Axel-Cyrille Ngonga Ngomo. “Neural Class Expression Synthesis.” ArXiv:2111.08486, 2021.
N. J. KOUAGOU, S. Heindorf, C. Demir, and A.-C. Ngonga Ngomo, “Neural Class Expression Synthesis,” arXiv:2111.08486. 2021.
KOUAGOU, N’Dah Jean, et al. “Neural Class Expression Synthesis.” ArXiv:2111.08486, 2021.
All files available under the following license(s):
Copyright Statement:
This Item is protected by copyright and/or related rights. [...]

Link(s) to Main File(s)
Access Level
Restricted Closed Access

Export

Marked Publications

Open Data LibreCat

Sources

arXiv 2111.08486

Search this title in

Google Scholar