Publications (7)
Relating melting trends and elasticity in simple metals: an empirical potential approach
Alan Nichol, Graeme J. Ackland
We demonstrate that the melting points and other thermodynamic quantities of the alkali metals can be calculated based on static crystalline properties. To do this we derive analyt…
DIET: Lightweight Language Understanding for Dialogue Systems
Tanja Bunk, Daksh Varshneya, Vladimir Vlasov +1
Large-scale pre-trained language models have shown impressive results on language understanding benchmarks like GLUE and SuperGLUE, improving considerably over other pre-training m…
Task-Oriented Dialogue with In-Context Learning
Tom Bocklisch, Thomas Werkmeister, Daksh Varshneya +1
We describe a system for building task-oriented dialogue systems combining the in-context learning abilities of large language models (LLMs) with the deterministic execution of bus…
Where is the context? -- A critique of recent dialogue datasets
Johannes E. M. Mosig, Vladimir Vlasov, Alan Nichol
Recent dialogue datasets like MultiWOZ 2.1 and Taskmaster-1 constitute some of the most challenging tasks for present-day dialogue models and, therefore, are widely used for system…
Few-Shot Generalization Across Dialogue Tasks
Vladimir Vlasov, Akela Drissner-Schmid, Alan Nichol
Machine-learning based dialogue managers are able to learn complex behaviors in order to complete a task, but it is not straightforward to extend their capabilities to new domains.…
Rasa: Open Source Language Understanding and Dialogue Management
Tom Bocklisch, Joey Faulkner, Nick Pawlowski +1
We introduce a pair of tools, Rasa NLU and Rasa Core, which are open source python libraries for building conversational software. Their purpose is to make machine-learning based d…