SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2006.06226 · ACL · 2020

Discrete Latent Variable Representations for Low-Resource Text Classification

Karl Stratos, Sam Wiseman, Karen Livescu, Shuning Jin

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

While much work on deep latent variable models of text uses continuous latent variables, discrete latent variables are interesting because they are more interpretable and typically more space efficient. We consider several approaches to learning discrete latent variable models for text in the case where exact marginalization over these variables is intractable. We compare the performance of the learned representations as features for lowresource document and sentence classification. Our best models outperform the previous best reported results with continuous representations in these low-resource settings, while learning significantly more compressed representations. Interestingly, we find that an amortized variant of Hard EM performs particularly well in the lowest-resource regimes. 1

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2006.06226")
get_code_for_paper("2006.06226")
have("2006.06226")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2006.06226.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2006.06226.svg)](https://syntology.ai/paper/2006.06226)

Connect an agent — have() is free.