News

Presenting at AKBC 2022 πŸ‡¬πŸ‡§
In HyperVC, we use hyperbolic models with variable curvature to learn representations of temporal knowledge graphs for future fact prediction.
New preprint on clinical event extraction
In DICE, we introduce a data-efficient generative model for clinical event extraction and propose the first benchmark in the domain.
Presenting at EMNLP 2021 πŸ‡©πŸ‡΄
New EMNLP Findings paper. In HyperExpan, we use a more expressive hyperbolic space for taxonomy expansion.
Presenting at NAACL 2021 🌎
We present our demo system EventPlus at NAACL 2021, the live system and code is released. Check it out!