Towards Computational Models for a Long-term Interaction with an Artificial Conversational Companion

Sviatlana Danilava, Stephan Busemann, Christoph Schommer, Gudrun Ziegler

2013

Abstract

In this paper we describe a design approach for an Artificial Conversational Companion according to earlier identified requirements of utility, adaptivity, conversational capabilities and long-term interaction. The Companion is aimed to help advanced learners of a foreign language to practice conversation via instant messenger dialogues. In order to model a meaningful long-term interaction with an Artificial Conversational Companion for this application case, it is necessary to understand how natural long-term interaction via chat between human language experts and language learners works. For this purpose, we created a corpus from instant messenger-based interactions between native speakers of German and advanced learners of German as a foreign language. We used methods from conversation analysis to identify rules of interaction. Examples from our data set are used to illustrate how particular requirements for the agent can be fulfilled. Finally, we outline how the identified patterns of interaction can be used for the design of an Artificial Conversational Companion.

Download


Paper Citation


in Harvard Style

Danilava S., Busemann S., Schommer C. and Ziegler G. (2013). Towards Computational Models for a Long-term Interaction with an Artificial Conversational Companion . In Proceedings of the 5th International Conference on Agents and Artificial Intelligence - Volume 1: ICAART, ISBN 978-989-8565-38-9, pages 241-247. DOI: 10.5220/0004255402410247

in Bibtex Style

@conference{icaart13,
author={Sviatlana Danilava and Stephan Busemann and Christoph Schommer and Gudrun Ziegler},
title={Towards Computational Models for a Long-term Interaction with an Artificial Conversational Companion},
booktitle={Proceedings of the 5th International Conference on Agents and Artificial Intelligence - Volume 1: ICAART,},
year={2013},
pages={241-247},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004255402410247},
isbn={978-989-8565-38-9},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 5th International Conference on Agents and Artificial Intelligence - Volume 1: ICAART,
TI - Towards Computational Models for a Long-term Interaction with an Artificial Conversational Companion
SN - 978-989-8565-38-9
AU - Danilava S.
AU - Busemann S.
AU - Schommer C.
AU - Ziegler G.
PY - 2013
SP - 241
EP - 247
DO - 10.5220/0004255402410247