research
∙
06/12/2023
Contrastive Attention Networks for Attribution of Early Modern Print
In this paper, we develop machine learning techniques to identify unknow...
share
research
∙
03/24/2022
Mix and Match: Learning-free Controllable Text Generation using Energy Language Models
Recent work on controlled text generation has either required attribute-...
research
∙
03/08/2022
Quantifying Privacy Risks of Masked Language Models Using Membership Inference Attacks
The wide adoption and application of Masked language models (MLMs) on se...
research
∙
06/04/2021
Exposing the Implicit Energy Networks behind Masked Language Models via Metropolis–Hastings
While recent work has shown that scores from models trained by the ubiqu...
research
∙
05/04/2020
A Probabilistic Generative Model for Typographical Analysis of Early Modern Printing
We propose a deep and interpretable probabilistic generative model to an...
research
∙
04/15/2019
An Empirical Investigation of Global and Local Normalization for Recurrent Neural Sequence Models Using a Continuous Relaxation to Beam Search
Globally normalized neural sequence models are considered superior to th...
research
∙
08/01/2017
A Continuous Relaxation of Beam Search for End-to-end Training of Neural Sequence Models
Beam search is a desirable choice of test-time decoding algorithm for ne...
research
∙
04/23/2017