# Event Representation with Sequential, Semi-Supervised Discrete Variables

arXiv: https://arxiv.org/abs/2010.04361 · HTML: https://mlsanity.com/paper/2010.04361/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Oct 2020.

## Built on by (most cited first, 8 of 8)

- [A Review of the Gumbel-max Trick and its Extensions for Discrete Stochasticity in Machine Learning](https://mlsanity.com/paper/2110.01515/) (2021)
- [Improving Event Representation via Simultaneous Weakly Supervised Contrastive Learning and Clustering](https://mlsanity.com/paper/2203.07633/) (2022)
- [Learning with Latent Structures in Natural Language Processing: A Survey](https://mlsanity.com/paper/2201.00490/) (2022)
- [Semantically-informed Hierarchical Event Modeling](https://mlsanity.com/paper/2212.10547/) (2022)
- [Sparse Universum Quadratic Surface Support Vector Machine Models for Binary Classification](https://mlsanity.com/paper/2104.01331/) (2021)
- [RevUp: Revise and Update Information Bottleneck for Event Representation](https://mlsanity.com/paper/2205.12248/) (2022)
- [Modeling Complex Event Scenarios via Simple Entity-focused Questions](https://mlsanity.com/paper/2302.07139/) (2023)
- [PromptCL: Improving Event Representation via Prompt Template and Contrastive Learning](https://mlsanity.com/paper/2404.17877/) (2024)

## Abstract (arXiv)

Within the context of event modeling and understanding, we propose a new method for neural sequence modeling that takes partially-observed sequences of discrete, external knowledge into account. We construct a sequential neural variational autoencoder, which uses Gumbel-Softmax reparametrization within a carefully defined encoder, to allow for successful backpropagation during training. The core idea is to allow semi-supervised external discrete knowledge to guide, but not restrict, the variational latent parameters during training. Our experiments indicate that our approach not only outperforms multiple baselines and the state-of-the-art in narrative script induction, but also converges more quickly.