A Classification-Based Approach to Automating Human-Robot Dialogue (bibtex)
by Gervits, Felix, Leuski, Anton, Bonial, Claire, Gordon, Carla and Traum, David
Abstract:
We present a dialogue system based on statistical classification which was used to automate human-robot dialogue in a collaborative navigation domain. The classifier was trained on a small corpus of multi-floor Wizard-of-Oz dialogue including two wizards: one standing in for dialogue capabilities and another for navigation. Below, we describe the implementation details of the classifier and show how it was used to automate the dialogue wizard. We evaluate our system on several sets of source data from the corpus and find that response accuracy is generally high, even with very limited training data. Another contribution of this work is the novel demonstration of a dialogue manager that uses the classifier to engage in multifloor dialogue with two different human roles. Overall, this approach is useful for enabling spoken dialogue systems to produce robust and accurate responses to natural language input, and for robots that need to interact with humans in a team setting.
Reference:
A Classification-Based Approach to Automating Human-Robot Dialogue (Gervits, Felix, Leuski, Anton, Bonial, Claire, Gordon, Carla and Traum, David), In .
Bibtex Entry:
@article{gervits_classication-based_nodate,
	title = {A {Classification}-{Based} {Approach} to {Automating} {Human}-{Robot} {Dialogue}},
	url = {https://link.springer.com/chapter/10.1007/978-981-15-9323-9_10},
	doi = {https://doi.org/10.1007/978-981-15-9323-9_10},
	abstract = {We present a dialogue system based on statistical classification which was used to automate human-robot dialogue in a collaborative navigation domain. The classifier was trained on a small corpus of multi-floor Wizard-of-Oz dialogue including two wizards: one standing in for dialogue capabilities and another for navigation. Below, we describe the implementation details of the classifier and show how it was used to automate the dialogue wizard. We evaluate our system on several sets of source data from the corpus and find that response accuracy is generally high, even with very limited training data. Another contribution of this work is the novel demonstration of a dialogue manager that uses the classifier to engage in multifloor dialogue with two different human roles. Overall, this approach is useful for enabling spoken dialogue systems to produce robust and accurate responses to natural language input, and for robots that need to interact with humans in a team setting.},
	language = {en},
	author = {Gervits, Felix and Leuski, Anton and Bonial, Claire and Gordon, Carla and Traum, David},
	keywords = {UARC, Virtual Humans, ARL, Dialogue},
	pages = {13},
	file = {Gervits et al. - A Classification-Based Approach to Automating Human.pdf:files/1746/Gervits et al. - A Classification-Based Approach to Automating Human.pdf:application/pdf},
}
Powered by bibtexbrowser