This survey discusses how recent developments in multimodal processing facilitate
conceptual grounding of language. We categorize the information flow in multimodal …

In this paper we introduce a practical first step towards the creation of an automated debate
agent: a state-of-the-art recurrent predictive model for predicting debate winners. By having …

Understanding uncertainty plays a critical role in achieving common ground (Clark et al.,
1983). This is especially important for multimodal AI systems that collaborate with users to …

Identifying persuasive speakers in an adversarial environment is a critical task. In a national
election, politicians would like to have persuasive speakers campaign on their behalf. When …

Debates are popular among politicians, journalists and scholars because they are a useful
way to foster discussion and argumentation about relevant matters. In these discussions …

Human behaviors in a group setting involve a complex mixture of multiple modalities: audio,
visual, linguistic, and human interactions. With the rapid progress of AI, automatic prediction …

In this dissertation, we address the task of argument mining, which encompasses numerous
subtasks. Our work specifically focuses on the tasks of identifying argument structure and …