An Embodied Incremental Bayesian Model of Cross-Situational Word Learning

Sepideh Sadeghi and Matthias Scheutz and Evan Krause

We present an incremental Bayesian model of cross-situational word learning with limited access to past situations and demonstrate its superior performance compared to other baseline incremental models, especially in the presence of sensory noise in speech and object recognition. Then, we embed our model in a cognitive robotic architecture and demonstrate the first scalable robotic model capable of incremental and open-world cross-situational word learning.

@inproceedings{sadeghi2017icdl,
  title={An Embodied Incremental Bayesian Model of Cross-Situational Word Learning},
  author={Sepideh Sadeghi and Matthias Scheutz and Evan Krause},
  year={2017},
  booktitle={proceedings of the 2017 Joint IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)},
  url={https://hrilab.tufts.edu/publications/sadeghi2017icdl.pdf}
}