# Hierarchical Quantized Representations for Script Generation

arXiv: https://arxiv.org/abs/1808.09542 · HTML: https://mlsanity.com/paper/1808.09542/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Aug 2018.

## Built on by (most cited first, 10 of 10)

- [proScript: Partially Ordered Scripts Generation via Pre-trained Language Models](https://mlsanity.com/paper/2104.08251/) (2021)
- [Salience-Aware Event Chain Modeling for Narrative Understanding](https://mlsanity.com/paper/2109.10475/) (2021)
- [Recent Advances in Neural Text Generation: A Task-Agnostic Survey](https://mlsanity.com/paper/2203.03047/) (2022)
- [Induce, Edit, Retrieve: Language Grounded Multimodal Schema for Instructional Video Retrieval](https://mlsanity.com/paper/2111.09276/) (2021)
- [Machine-Assisted Script Curation](https://mlsanity.com/paper/2101.05400/) (2021)
- [Semantically-informed Hierarchical Event Modeling](https://mlsanity.com/paper/2212.10547/) (2022)
- [Causal Graph based Event Reasoning using Semantic Relation Experts](https://mlsanity.com/paper/2506.06910/) (2025)
- [Synergizing Unsupervised Episode Detection with LLMs for Large-Scale News Events](https://mlsanity.com/paper/2408.04873/) (2024)
- [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)

## Abstract (arXiv)

Scripts define knowledge about how everyday scenarios (such as going to a restaurant) are expected to unfold. One of the challenges to learning scripts is the hierarchical nature of the knowledge. For example, a suspect arrested might plead innocent or guilty, and a very different track of events is then expected to happen. To capture this type of information, we propose an autoencoder model with a latent space defined by a hierarchy of categorical variables. We utilize a recently proposed vector quantization based approach, which allows continuous embeddings to be associated with each latent variable value. This permits the decoder to softly decide what portions of the latent hierarchy to condition on by attending over the value embeddings for a given setting. Our model effectively encodes and generates scripts, outperforming a recent language modeling-based method on several standard tasks, and allowing the autoencoder model to achieve substantially lower perplexity scores compared to the previous language modeling-based method.