Papers by Mehdi Rezaee
RevUp: Revise and Update Information Bottleneck for Event Representation (2023.eacl-main)
Copied to clipboard
| Challenge: | Existing external (“side”) semantic knowledge has been shown to result in more expressive computational event models. |
| Approach: | They propose a semi-supervised information bottleneck-based discrete latent variable model that reparameterizes discrete variables with auxiliary continuous latent variables and a light-weight hierarchical structure. |
| Outcome: | The proposed model outperforms existing models on multiple datasets. |
Semantically-informed Hierarchical Event Modeling (2023.starsem-1)
Copied to clipboard
| Challenge: | Existing approaches to event modeling combine sequential latent variables with semantic ontological knowledge to improve representational capabilities. |
| Approach: | They propose a doubly hierarchical semi-supervised event modeling framework that provides structural hierarchy while accounting for ontological hierarchy. |
| Outcome: | The proposed model outperforms state-of-the-art models by 8.5% across two datasets and four metrics. |
Event Representation with Sequential, Semi-Supervised Discrete Variables (2021.naacl-main)
Copied to clipboard
| Challenge: | Existing methods for event modeling take discrete, external knowledge into account . obtaining fully accurate structured knowledge can be difficult . |
| Approach: | They propose a method that takes partially-observed sequences of discrete, external knowledge into account. |
| Outcome: | The proposed method outperforms baselines and state-of-the-art in script induction and converges faster. |