A data-driven model of explanations for a chatbot that helps to practice conversation in a foreign language
English
Höhn, Sviatlana[University of Luxembourg > Faculty of Science, Technology and Communication (FSTC) > Computer Science and Communications Research Unit (CSC) >]
2017
Proceedings of SIGDial 2017
Yes
International
Sviatlana Höhn
2017 August
SIGDial
Saarbrücken
Germany
[en] Chatbots ; Repair ; ICALL
[en] This article describes a model of other-initiated self-repair for a chatbot that helps to practice conversation in a foreign lan- guage. The model was developed using a corpus of instant messaging conversations between German native and non-native speakers. Conversation Analysis helped to create computational models from a small number of examples. The model has been validated in an AIML-based chatbot. Unlike typical retrieval-based dialogue systems, the explanations are generated at run-time from a linguistic database.