Longitudinal Dialogues: Data Collection, Personalization, Dialogue Modelling, and Evaluation

Abstract

Longitudinal Dialogues (LD) are the most challenging type of conversation for human-machine dialogue systems. LDs include the recollections of events, personal thoughts, and emotions specific to each individual in a sparse sequence of dialogue sessions. Dialogue systems designed for LDs should uniquely interact with the users over multiple sessions and long periods of time (e.g. weeks), and engage them in personal dialogues to elaborate on their feelings, thoughts, and real-life events.

In this talk, the speaker presents the process of designing and training dialogue models for LDs, starting from the acquisition of a multi-session dialogue corpus in the mental health domain, models for user profiling, and personalization, to fine-tuning SOTA Pre-trained Language Models and the evaluation of the models using human judges

How to participate

It is also possible to follow the seminar on Zoom. In order to get the link, please send an e-mail to mahed.mousavi [at] unitn.it