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 optimizing dialogue success.Until now, categorical posteriors have been argued to be one of the main drivers of performance. In this work we revisit Gaussian variational posteriors for latent-action RL and show that they can yield even better performance than categoricals. We achieve this by introducing an improved variational inference objective for learning continuous representations without auxiliary learning objectives, which streamlines the training procedure. Moreover, we propose ways to regularize the latent dialogue policy, which helps to retain good response c...
In spoken dialogue systems, we aim to deploy artificial intelligence to build automated dialogue age...
Spoken dialogue systems allow humans to interact with machines using natural speech. As such, they h...
Reinforcement Learning methods are capable of solving complex problems, but resulting policies might...
Recently, two approaches, fine-tuning large pre-trained language models and variational training, ha...
Despite its significant effectiveness in adversarial training approaches to multidomain task-oriente...
Variational encoder-decoders (VEDs) have shown promising results in dialogue generation. However, th...
Conditional variational models, using either continuous or discrete latent variables, are powerful f...
Dialogue policy learning for task-oriented dialogue systems has enjoyed great progress recently most...
We present a novel architecture for explainable modeling of task-oriented dialogues with discrete la...
This thesis explores Bayesian and variational inference in the context of solving the reinforcement ...
We present a novel architecture for explainable modeling of task-oriented dialogues with discrete la...
Variational Auto Encoder (VAE) provide an efficient latent space representation of complex data dist...
In spoken dialogue systems, we aim to deploy artificial intelligence to build automated dialogue age...
textabstractMany traditional reinforcement-learning algorithms have been designed for problems with ...
Spoken dialogue systems allow humans to interact with machines using natural speech. As such, they h...
In spoken dialogue systems, we aim to deploy artificial intelligence to build automated dialogue age...
Spoken dialogue systems allow humans to interact with machines using natural speech. As such, they h...
Reinforcement Learning methods are capable of solving complex problems, but resulting policies might...
Recently, two approaches, fine-tuning large pre-trained language models and variational training, ha...
Despite its significant effectiveness in adversarial training approaches to multidomain task-oriente...
Variational encoder-decoders (VEDs) have shown promising results in dialogue generation. However, th...
Conditional variational models, using either continuous or discrete latent variables, are powerful f...
Dialogue policy learning for task-oriented dialogue systems has enjoyed great progress recently most...
We present a novel architecture for explainable modeling of task-oriented dialogues with discrete la...
This thesis explores Bayesian and variational inference in the context of solving the reinforcement ...
We present a novel architecture for explainable modeling of task-oriented dialogues with discrete la...
Variational Auto Encoder (VAE) provide an efficient latent space representation of complex data dist...
In spoken dialogue systems, we aim to deploy artificial intelligence to build automated dialogue age...
textabstractMany traditional reinforcement-learning algorithms have been designed for problems with ...
Spoken dialogue systems allow humans to interact with machines using natural speech. As such, they h...
In spoken dialogue systems, we aim to deploy artificial intelligence to build automated dialogue age...
Spoken dialogue systems allow humans to interact with machines using natural speech. As such, they h...
Reinforcement Learning methods are capable of solving complex problems, but resulting policies might...