Download PDFOpen PDF in browser

CoRg: Commonsense Reasoning Using a Theorem Prover and Machine Learning

7 pagesPublished: May 25, 2019

Abstract

Commonsense reasoning is an everyday task that is intuitive for humans but hard to implement for computers. It requires large knowledge bases to get the required data from, although this data is still incomplete or even inconsistent. While machine learning algorithms perform rather well on these tasks, the reasoning process remains a black box. To close this gap, our system CoRg aims to build an explainable and well-performing system, which consists of both an explainable deductive derivation process and a machine learning part. We conduct our experiments on the Copa question-answering benchmark using the ontologies WordNet, Adimen-SUMO, and ConceptNet. The knowledge is fed into the theorem prover Hyper and in the end the conducted models will be analyzed using machine learning algorithms, to derive the most probable answer.

Keyphrases: cognitive reasoning, commonsense reasoning, Explainable Artificial Intelligence, Ontologies, theorem proving

In: Christoph Benzmüller, Xavier Parent and Alexander Steen (editors). Selected Student Contributions and Workshop Papers of LuxLogAI 2018, vol 10, pages 20--26

Links:
BibTeX entry
@inproceedings{LuxLogAI2018:CoRg_Commonsense_Reasoning_Using,
  author    = {Sophie Siebert and Frieder Stolzenburg},
  title     = {CoRg: Commonsense Reasoning Using a Theorem Prover and Machine Learning},
  booktitle = {Selected Student Contributions and Workshop Papers of LuxLogAI 2018},
  editor    = {Christoph Benzm\textbackslash{}"uller and Xavier Parent and Alexander Steen},
  series    = {Kalpa Publications in Computing},
  volume    = {10},
  pages     = {20--26},
  year      = {2019},
  publisher = {EasyChair},
  bibsource = {EasyChair, https://easychair.org},
  issn      = {2515-1762},
  url       = {https://easychair.org/publications/paper/hDX6},
  doi       = {10.29007/lt5p}}
Download PDFOpen PDF in browser