Search Results for author:
Found 3 papers, 2 papers with code
Sequence-to-Sequence Pre-training with Unified Modality Masking for Visual Document Understanding
This paper presents GenDoc, a general sequence-to-sequence document understanding model pre-trained with unified masking across three modalities: text, image, and layout.
document understanding
Optical Character Recognition (OCR)
+1
Variational Autoencoder with Disentanglement Priors for Low-Resource Task-Specific Natural Language Generation
In this paper, we propose a variational autoencoder with disentanglement priors, VAE-DPRIOR, for task-specific natural language generation with none or a handful of task-specific labeled examples.
A Framework for Deep Constrained Clustering
A fundamental strength of deep learning is its flexibility, and here we explore a deep learning framework for constrained clustering and in particular explore how it can extend the field of constrained clustering.
