LD-SDS: Towards an Expressive Spoken Dialogue System based on Linked-Data
share
In this work we discuss the related challenges and describe an approach towards the fusion of state-of-the-art technologies from the Spoken Dialogue Systems (SDS) and the Semantic Web and Information Retrieval domains. We envision a dialogue system named LD-SDS that will support advanced, expressive, and engaging user requests, over multiple, complex, rich, and open-domain data sources that will leverage the wealth of the available Linked Data. Specifically, we focus on: a) improving the identification, disambiguation and linking of entities occurring in data sources and user input; b) offering advanced query services for exploiting the semantics of the data, with reasoning and exploratory capabilities; and c) expanding the typical information seeking dialogue model (slot filling) to better reflect real-world conversational search scenarios.
READ FULL TEXT