Xi Peng
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Xi Peng has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Robert Hoehndorf
King Abdullah University of Science and Technology
2 shared publications - Zhenwei Tang
University of Toronto University of Toronto Harvard University Cornell University Microsoft Research University of Toronto
2 shared publications - Fuzhen Zhuang
School of Artificial Intelligence, Beihang University, Beijing, China
1 shared publication - Shichao Pei
University of Notre Dame
1 shared publication - Tilman Hinnerichs
TU Delft van Mourik Broekmanweg 6 2628 XE Delft The Netherlands
1 shared publication - Xiangliang Zhang
University of Notre Dame
1 shared publication
Latest Publications
- 27 October 2023
- Published by Springer Nature
- p. 522-540
Neural Multi-hop Logical Query Answering with Concept-Level Answers
- 27 October 2023
- Published by Springer Nature
- p. 522-540
Neural Multi-hop Logical Query Answering with Concept-Level Answers
- Open Access
FALCON: Faithful Neural Semantic Entailment over ALC Ontologies
Many ontologies, i.e., Description Logic (DL) knowledge bases, have been developed to provide rich knowledge about various domains, and a lot of them are based on ALC, i.e., a prototypical and expressive DL, or its extensions. The main task that explores ALC ontologies is to compute semantic entailment. We developed FALCON, a Fuzzy ALC Ontology Neural reasoner, which uses fuzzy logic operators to generate model structures for arbitrary ALC ontologies, and uses multiple model structures to compute faithful semantic entailments. Theoretical results show that FALCON faithfully approximates semantic entailment over ALC ontologies and therefore endows neural networks with world models and the ability to reason over them. Experimental results show that FALCON enables approximate reasoning, paraconsistent reasoning (reasoning with inconsistencies), and improves machine learning in the biomedical domain by incorporating knowledge expressed in ALC.
Open AccessFALCON: Faithful Neural Semantic Entailment over ALC Ontologies
Many ontologies, i.e., Description Logic (DL) knowledge bases, have been developed to provide rich knowledge about various domains, and a lot of them are based on ALC, i.e., a prototypical and expressive DL, or its extensions. The main task that explores ALC ontologies is to compute semantic entailment. We developed FALCON, a Fuzzy ALC Ontology Neural reasoner, which uses fuzzy logic operators to generate model structures for arbitrary ALC ontologies, and uses multiple model structures to compute faithful semantic entailments. Theoretical results show that FALCON faithfully approximates semantic entailment over ALC ontologies and therefore endows neural networks with world models and the ability to reason over them. Experimental results show that FALCON enables approximate reasoning, paraconsistent reasoning (reasoning with inconsistencies), and improves machine learning in the biomedical domain by incorporating knowledge expressed in ALC.