🗣️ Mediums, Modalities and Conversational Components
In this article I talk about mediums, modalities and conversational components. And how certain intents are best suited for specific mediums, modalities and conversational components.
A medium is the access point for the conversation, it could be speech via a telephone, a text based conversation, a kiosk at a drive-through, a TV, a vehicle, etc.
A modality lives within the medium and can take various shapes…according to Apple…
Modality is a design technique that presents content in a separate, focused mode that prevents interaction with the parent view and requires an explicit action to dismiss.~ Apple
I would argue that within a Conversational User Interface (CUI) to force a user to explicitly dismiss actions are perhaps not a necessity. Also in the case of CUIs, a mixed modality approach can work well.
For instance in the case of an Echo Show, where the conversation can start in user voice input, and the response is rendered by the skill in speech, Graphics, and touch options.
In turn the user can respond with speech, touch, and in some rare implementations, gestures (NVIDIA Riva).
💬 Conversational Components / Design Affordances
Conversational Components can be considered as tools and methods to be used in different modalities. And in turn a modality can live within a medium.
Depending on the medium, different components can be used to create a multi-modal experience.
These conversational components or design affordances can be in the shape of table views, images, maps, buttons, carousels, etc. Obviously certain mediums and modalities offer more and richer design affordances.
For instance, accessing a CUI via Facebook Messenger, and the medium of a mobile phone, rich design affordances are available to the user, as seen in the image below:
It needs to be stated that intents remain the frontline of customer interactions with any Conversational UI. This has recently been confirmed by research from Gartner; failing to start any Conversational UI journey by determining existing user intent is a preamble for poor uptake and problem resolution.
Intent Driven Design and Development is the starting point for astute NLU Design. The single mistake listed which accounted for most of the failures, was that organisations start with technology choices and not with customer intent.
In a follow-up article I will be discussing examples where user intent cannot be fully supported by a multi-turn dialog approach…and a multi-modal approach is necessitated…
I’m currently the Chief Evangelist @ HumanFirst. I explore and write about all things at the intersection of AI and language; ranging from LLMs, Chatbots, Voicebots, Development Frameworks, Data-Centric latent spaces and more.
NLU design tooling
“Conversation Designer, Retail, 10k+ employees The tool that turned conversation designers, into NLU designers” ★★★★★…
Get an email whenever Cobus Greyling publishes.
Get an email whenever Cobus Greyling publishes. By signing up, you will create a Medium account if you don’t already…
Eliza Language Technology Community — Language Technology: Conversational AI, NLP/NLP, CCAI…
ELIZA — Where language technology enthusiasts unite.
Key Considerations In Designing A Conversational User Interface
Start Here If You are Thinking Of Creating A Chatbot
The Cobus Quadrant™ Of NLU Design
NLU design is vital to planning and continuously improving Conversational AI experiences.
The Cobus Quadrant™ Of Conversation Design Capabilities
∗ This is part one of a two part series, please also take a look part two, the Cobus Quadrant of NLU Design.