Semantic Role Labelling for Robot Instructions using Echo State Networks - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2016

Semantic Role Labelling for Robot Instructions using Echo State Networks

Abstract

To control a robot in a real-world robot scenario, a real-time parser is needed to create semantic representations from natural language which can be interpreted. The parser should be able to create the hierarchical tree-like representations without consulting external systems to show its learning capabilities. We propose an efficient Echo State Network-based parser for robotic commands and only relies on the training data. The system generates a single semantic tree structure in real-time which can be executed by a robot arm manipulating objects. Four of six other approaches, which in most cases generate multiple trees and select one of them as the solution, were outperformed with 64.2% tree accuracy on difficult unseen natural language (74.1% under best conditions) on the same dataset.
Fichier principal
Vignette du fichier
Twiefel_ESANN_2016_camera_ready.pdf (382.84 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01417701 , version 1 (15-12-2016)

Identifiers

  • HAL Id : hal-01417701 , version 1

Cite

Johannes Twiefel, Xavier Hinaut, Stefan Wermter. Semantic Role Labelling for Robot Instructions using Echo State Networks. European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN), Apr 2016, Bruges, Belgium. ⟨hal-01417701⟩

Collections

CNRS INRIA INRIA2
449 View
147 Download

Share

Gmail Facebook X LinkedIn More