Human-human dialogues are characterized by collaborative behaviors, through which interlocutors achieve their communicative goals. As an example, proactivity (i.e., anticipating user needs during dialogue) and grounding (e.g., clarification questions) are two relevant cases that have been investigated from a linguistics perspective. However, such collaborative behaviors are still largely absent in current neural dialogue models. There are several open research challenges in this direction, including investigating how dialogue systems can learn when and how to be collaborative, depending on the dialogue context, and how do we evaluate whether collaborative behaviors have improved the efficacy of dialogue.

This PhD project addresses collaborative behaviors in conversational agents from a computational perspective, exploiting the integration of machine learning approaches based on neural models, reinforcement learning, and knowledge-based techniques.