LD-SDS: Towards an Expressive Spoken Dialogue System based on Linked-Data
This work addresses the problem of enhancing conversational AI for more natural and engaging user interactions with rich data sources, though it appears incremental as it builds on existing SDS and semantic web technologies.
The paper tackles the challenge of creating an expressive spoken dialogue system that integrates semantic web technologies to handle complex, open-domain queries over linked data, aiming to improve entity linking, query semantics, and conversational models beyond slot-filling.
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.