Commonsense Reasoning Using Theorem Proving and Machine Learning - Archive ouverte HAL Access content directly
Conference Papers Year : 2019

Commonsense Reasoning Using Theorem Proving and Machine Learning

(1) , (2) , (1)
1
2
Sophie Siebert
  • Function : Author
  • PersonId : 1067004
Claudia Schon
  • Function : Author
  • PersonId : 1067006
Frieder Stolzenburg
  • Function : Author
  • PersonId : 1067008

Abstract

Commonsense reasoning is a difficult task for a computer to handle. Current algorithms score around 80% on benchmarks. Usually these approaches use machine learning which lacks explainability, however. Therefore, we propose a combination with automated theorem proving here. Automated theorem proving allows us to derive new knowledge in an explainable way, but suffers from the inevitable incompleteness of existing background knowledge. We alleviate this problem by using machine learning. In this paper, we present our approach which uses an automatic theorem prover, large existing ontologies with background knowledge, and machine learning. We present first experimental results and identify an insufficient amount of training data and lack of background knowledge as causes for our system not to stand out much from the baseline.
Fichier principal
Vignette du fichier
485369_1_En_25_Chapter.pdf (258.27 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-02520044 , version 1 (26-03-2020)

Licence

Attribution - CC BY 4.0

Identifiers

Cite

Sophie Siebert, Claudia Schon, Frieder Stolzenburg. Commonsense Reasoning Using Theorem Proving and Machine Learning. 3rd International Cross-Domain Conference for Machine Learning and Knowledge Extraction (CD-MAKE), Aug 2019, Canterbury, United Kingdom. pp.395-413, ⟨10.1007/978-3-030-29726-8_25⟩. ⟨hal-02520044⟩
30 View
20 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More