Jennifer Lee — accepted AI-conference papers

2021

Conversational Multi-Hop Reasoning with Neural Commonsense Knowledge and Symbolic Logic Rules

Forough Arabshahi, Jennifer Lee, Antoine Bosselut, Yejin Choi, Tom Mitchell

EMNLP 2021main

One of the challenges faced by conversational agents is their inability to identify unstated presumptions of their users’ commands, a task trivial for humans due to their common sense. In this paper, we propose a zero-shot commonsense reasoning system for conversational agents in an attempt to achie…

Cited by 20 Source ↗PDF ↗code ↗Scholar ↗

2021

Conversational Neuro-Symbolic Commonsense Reasoning

Forough Arabshahi, Jennifer Lee, Mikayla Gawarecki, Kathryn Mazaitis, Amos Azaria, Tom Mitchell

AAAI 2021technical

In order for conversational AI systems to hold more natural and broad-ranging conversations, they will require much more commonsense, including the ability to identify unstated presumptions of their conversational partners. For example, in the command "If it snows at night then wake me up early beca…

Cited by 63 Source ↗PDF ↗code ↗Scholar ↗