Mattia Medina Grespan — accepted AI-conference papers

2023

Logic-driven Indirect Supervision: An Application to Crisis Counseling

Mattia Medina Grespan, Meghan Broadbent, Xinyao Zhang, Katherine Axford, Brent Kious, Zac Imel +1

ACL 2023long

Ensuring the effectiveness of text-based crisis counseling requires observing ongoing conversations and providing feedback, both labor-intensive tasks. Automatic analysis of conversations—at the full chat and utterance levels—may help support counselors and provide better care. While some session-le…

Cited by 1 Source ↗PDF ↗Scholar ↗

2021

Evaluating Relaxations of Logic for Neural Networks: A Comprehensive Study

Mattia Medina Grespan, Ashim Gupta, Vivek Srikumar

IJCAI 2021poster

Symbolic knowledge can provide crucial inductive bias for training neural models, especially in low data regimes. A successful strategy for incorporating such knowledge involves relaxing logical statements into sub-differentiable losses for optimization. In this paper, we study the question of how b…

Cited by 18 Source ↗PDF ↗code ↗Scholar ↗