- Ubiquitous –ambient, anytime and anywhere
- Accurate – maximally correct & complete
- Flexible – take more than one type of modality as a query to retrieve relevant data in any type of modality
- Relevant - provide the most relevant information to the user, learn to adapt to user behavior, to understand the user search intents
- Intelligent – generate well-formed and meaningful responses based on retrieved information and context
- Humane – leverage human-curated knowledge bases, present human-readable results, adopt linguistically and culturally appropriate dialogue patterns
- Safe – preserve privacy, prevent undesirable or harmful content
In order to realise this next generation search technology, the DReaMS Lab will investigate Multimodal Dialogue Search Systems, focusing on three main approaches:
Dialogues, REAsoning and Multi-linguality for Search.
The DREAMS Lab is a collaboration between the Computational Lexicology & Terminology Lab (CLTL, Prof. dr. Piek Vossen) and the Knowledge Representation and Reasoning group (KRR, Prof. dr. Frank van Harmelen), both at VU Amsterdam; the Information and Language Processing Systems at the UVA (Prof. dr. Maarten de Rijke) and the Huawei Consumer Business Group, a world leading provider of cloud services for customers. At full strength, the DREAMS Lab will employ up to nine people (PostDocs and PhD students).