Blog
The future of conversational AI
We look into our Artificial Intelligence crystal ball to come up with some predictions on what we can expect from in conversational AI in the next...
Blog
How we use open source deep learning models
Explore the open source developments that help power raffle.ai's innovative AI solutions for customer service and knowledge sharing.
Blog
The science behind the raffle-lution: Natural language search
Learn how raffle.ai have learned from search developments in AI to fine-tune their customer support products.
Research
End-to-end information extraction from documents
Document information extraction tasks performed by humans create data consisting of a PDF or document image input, and extracted string outputs.
Blog
How language modelling has changed NLP
How do we make our AI customer support tools? What state-of-the-art technology do we use? Our CTO explains all.
Blog
Conversational AI: to chatbot or not to chatbot?
You've read about chatbots but aren't sure whether they're right for you — our AI expert discusses when decison tree-based chatbots do and don't work
Research
A disentangled recognition and nonlinear dynamics model for
This paper takes a step towards temporal reasoning in a dynamically changing video in a latent space.
Research
Semi-supervised generation with cluster-aware generative models
Deep generative models trained with large amounts of unlabelled data have proven to be powerful within the domain of unsupervised learning.
Blog
raffle is data-driven about AI
Applying a data-driven approach means we use training data instead of defining rules, distinguishing ourselves from traditional chatbots.