Hierarchical Quantized Representations for Script Generation
Abstract
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.
Cite
@article{arxiv.1808.09542,
title = {Hierarchical Quantized Representations for Script Generation},
author = {Noah Weber and Leena Shekhar and Niranjan Balasubramanian and Nathanael Chambers},
journal= {arXiv preprint arXiv:1808.09542},
year = {2018}
}
Comments
EMNLP 2018