An Analysis of Subtask-Dependency in Robot Command Interpretation with Dilated CNNs

Proceedings of the 26th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN 2018), pages 25--30 - Apr 2018.
Associated documents : es2018-96.pdf [1.4Mo]  
In this paper, we tackle sequence-to-tree transduction for language processing with neural networks implementing several subtasks, namely tokenization, semantic annotation, and tree generation. Our research question is how the individual subtasks influence the overall end-toend learning performance in case of a convolutional network with dilated perceptive fields. We investigate a benchmark problem for robot command interpretation and conclude that dilation has a strong positive effect for performing character-level transduction and for generating parsing trees.

 

@InProceedings{EAAW18,
  author       = "Eppe, Manfred and Alpay, Tayfun and Abawi, Fares and Wermter, Stefan",
  title        = "An Analysis of Subtask-Dependency in Robot Command Interpretation with Dilated CNNs",
  booktitle    = "Proceedings of the 26th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN 2018)",
  pages        = "25--30",
  month        = "Apr",
  year         = "2018",
  address      = "Bruges, Belgium",
  url          = "https://www2.informatik.uni-hamburg.de/wtm/publications/2018/EAAW18/es2018-96.pdf"
}

» Manfred Eppe
» Tayfun Alpay
» Fares Abawi
» Stefan Wermter