A Framework for Resolving Open-World Referential Expressions in Distributed Heterogeneous Knowledge Bases

2016

Conference: Proceedings of the 30th AAAI Conference on Artificial Intelligence

Tom Williams and Matthias Scheutz

We present a domain-independent approach to reference resolution that allows a robotic or virtual agent to resolve references to entities (eg, objects and locations) found in open worlds when the information needed to resolve such references is distributed among multiple heterogeneous knowledge bases in its architecture. An agent using this approach can combine information from multiple sources without the computational bottleneck associated with centralized knowledge bases.

@inproceedings{williams2016aaai,
  title={A Framework for Resolving Open-World Referential Expressions in Distributed Heterogeneous Knowledge Bases},
  author={Tom Williams and Matthias Scheutz},
  year={2016},
  booktitle={Proceedings of the 30th AAAI Conference on Artificial Intelligence},
  url={https://hrilab.tufts.edu/publications/williams2016aaai.pdf}
}