Classication of Localization Utterances using a Spatial Ontology

International Workshop on Place-related Knowledge Acquisition Research

Mohammad Fazleh Elahi1, Hui Shi1, John A. Bateman1, Kathleen M. Eberhard2, Matthias Scheutz3 ; 2 Department of Psychology ; University of Notre Dame ; USA ; 3 Human-Robot Interaction Lab ; Tufts University ; USA

Others  :  http://ceur-ws.org/Vol-881/paper4.pdf
PID  :  43441

来源: CEUR

【 摘 要 】

Dialogue systems for spatially situated tasks need to providereferential descriptions of spatially located objects and understand such descriptions from users. To construct such dialogue systems, it is useful to investigate how humans describe object locations in their immediate environment and how they ask about object locations in remote envi- ronments. In this paper, we address the semantic classication of the localization utterances found in the CReST corpus, which is a dialogue corpus of humans performing a cooperative, remote, search task. The aim is to explore the relation between specic semantic congurations and the dialogically and situationally embedded linguistic forms employed. Specically, we rst extracted dierent types of localization utterances from the corpus and then paired these with semantic categories pro- vided by the linguistically motivated spatial ontology GUM. The paper concludes with a discussion of the characteristics of dierent types of localization expressions on the basis of spatial concepts and descriptions