3 papers
cs.CL2022
Deploying a Retrieval based Response Model for Task Oriented Dialogues
Lahari Poddar, György Szarvas, Cheng Wang +3
Task-oriented dialogue systems in industry settings need to have high conversational capability, be easily adaptable to changing situations and conform to business constraints. Thi…
cs.CL2022
Taming Continuous Posteriors for Latent Variational Dialogue Policies
Marin Vlastelica, Patrick Ernst, György Szarvas
Utilizing amortized variational inference for latent-action reinforcement learning (RL) has been shown to be an effective approach in Task-oriented Dialogue (ToD) systems for optim…
cs.LG2020
Learning to Rank in the Position Based Model with Bandit Feedback
Beyza Ermis, Patrick Ernst, Yannik Stein +1
Personalization is a crucial aspect of many online experiences. In particular, content ranking is often a key component in delivering sophisticated personalization results. Commonl…