Instead of typing keywords in a search bar, we would rather have a chat with a (virtual) librarian and express our ‘information need’ or interest in certain content in the archive in a conversation. At Netherlands Institute for Sound and Vision, we investigate several use cases in the area of Spoken Conversational Search (SCS) as a means to guide access to our rich but also large and heterogeneous audiovisual archive. In our LABS environment, we have search APIs built on top of indices of rich metadata that can be connected to a dialogue system that uses keyboard or speech input to communicate with users online and in our museum.
Thanks to progress in AI, natural language dialogues between humans and conversational agents are becoming a realistic option to help users of an archive such as NISV to express their information need. Especially in complex search tasks that require users to reference or be aware of the attributes of a collection (metadata), SCS dialogues can be used to guide users filling those attributes (facets) in the course of a mixed-initiative natural conversation.
Research questions we can think of:
Please contact us if you are interested to engage with our data and APIs for your research or development project.