RevUp: Revise and Update Information Bottleneck for Event Representation
This work addresses event representation for computational models, but it is incremental as it builds on existing information bottleneck methods with modifications.
The authors tackled the problem of noisy or missing side information in event modeling by proposing a semi-supervised information bottleneck-based discrete latent variable model with auxiliary continuous variables, achieving strong empirical performance that outperforms previous approaches on multiple datasets.
The existence of external (``side'') semantic knowledge has been shown to result in more expressive computational event models. To enable the use of side information that may be noisy or missing, we propose a semi-supervised information bottleneck-based discrete latent variable model. We reparameterize the model's discrete variables with auxiliary continuous latent variables and a light-weight hierarchical structure. Our model is learned to minimize the mutual information between the observed data and optional side knowledge that is not already captured by the new, auxiliary variables. We theoretically show that our approach generalizes past approaches, and perform an empirical case study of our approach on event modeling. We corroborate our theoretical results with strong empirical experiments, showing that the proposed method outperforms previous proposed approaches on multiple datasets.