← Search

Daniel Spokoyny

2 accepted papers

2022

Masked Measurement Prediction: Learning to Jointly Predict Quantities and Units from Textual Context

NAACL 2022findings

Physical measurements constitute a large portion of numbers in academic papers, engineering reports, and web tables. Current benchmarks fall short of properly evaluating numeracy of pretrained language models on measurements, hindering research on developing new methods and applying them to numerica…

2019

Lagging Inference Networks and Posterior Collapse in Variational Autoencoders

ICLR 2019poster

The variational autoencoder (VAE) is a popular combination of deep latent variable model and accompanying variational learning technique. By using a neural inference network to approximate the model's posterior on latent variables, VAEs efficiently parameterize a lower bound on marginal data likelih…