AI Paper Atlas

Research map / Probabilistic and scientific modeling / Variational and generative sampling

Differentiable Perturb-and-Parse: Semi-Supervised Parsing with a Structured Variational Autoencoder

Caio Corro, Ivan Titov

ICLR 2019 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Structured latent VAEs · 42 citations (OpenAlex)

Read the paper

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use semi-supervised VAE training with unlabeled sentencesDependency parser · English testUAS: ~88.79 -> 89.39Improved
Use semi-supervised VAE training with unlabeled sentencesDependency parser · French testUAS: 84.09 -> 84.43Improved
Use semi-supervised VAE training with unlabeled sentencesDependency parser · Swedish testUAS: 86.59 -> 86.92Improved
Remove latent sentence embedding z (ablation)VAE w. z · English testUAS: 89.39 -> 89.50Improved
Remove latent sentence embedding z (ablation)VAE w. z · French testLAS: 77.89 -> 78.49Improved
Remove latent sentence embedding z (ablation)VAE w. z · Swedish testLAS: 80.01 -> 79.80Hurt
Remove or heavily downweight the dependency-tree KL prior term (ablation)Semi-supervised VAE · English, French, and SwedishUASImproved
Use bi-affine attention in the parser (ablation)Semi-supervised VAE · Low-resource parsingUASNo clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy