General-purpose language models have demonstrated impressive capabilities, performing
on par with state-of-the-art approaches on a range of downstream natural language …

Dialogue systems powered by large pre-trained language models (LM) exhibit an innate
ability to deliver fluent and natural-looking responses. Despite their impressive generation …

Dialogue systems have made massive promising progress contributed by deep learning
techniques and have been widely applied in our life. However, existing end-to-end neural …

To diversify and enrich generated dialogue responses, knowledge-grounded dialogue has
been investigated in recent years. The existing methods tackle the knowledge grounding …

Abstract Information-seeking dialogue systems, including knowledge identification and
response generation, aim to respond to users with fluent, coherent, and informative …

In this thesis, we introduce Greenformers, a collection of model efficiency methods to
improve the model efficiency of the recently renowned transformer models with a low-rank …

The recent development of language models has shown promising results by achieving
state-of-the-art performance on various natural language tasks by fine-tuning pre-trained …

Many task-oriented dialogue systems use deep reinforcement learning (DRL) to learn
policies that respond to the user appropriately and complete the tasks successfully. Training …

Many task-oriented dialogue systems use deep reinforcement learning (DRL) to learn
policies that respond to the user appropriately and complete the tasks successfully. Training …

Incorporating personas information allows diverse and engaging responses in dialogue
response generation. Unfortunately, prior works have primarily focused on self personas …