Shipping Applied Research to Solve Real Problems

We are still in the early days of AI assistants and many things still need to be invented. Our research is driven by real challenges and datasets, and its primary aim is to let makers expand the capabilities of their AI assistants.

Latest publication

Few-Shot Generalization Across Dialogue Tasks

We introduce the Recurrent Embedding Dialogue Policy (REDP) which is designed to deal with uncooperative user behaviour and transfer dialogue patterns across tasks.

Building AI assistants is hard.

Our research is driven by real challenges and data sets.

Cross-task transfer learning

AI assistants should be able to help with more than one task. How can we re-use experience in learning one task to learn another faster?

Few-shot learning

Training data is a bottleneck in every conversational AI project. How can we build models that can learn from just a few examples?

Conversational Sentence Embeddings

How can we build sentence embeddings that are sensitive to the rules of conversation?

Our open source tools are used in research projects and papers in a growing number of leading institutions. In addition, our NLU has been benchmarked by TU Munich.