4 papers
NNN: Next-Generation Neural Networks for Marketing Measurement
Thomas Mulc, Mike Anderson, Paul Cubre +3
We present NNN, an experimental Transformer-based neural network approach to marketing measurement. Unlike Marketing Mix Models (MMMs) which rely on scalar inputs and parametric de…
Compressing Search with Language Models
Thomas Mulc, Jennifer L. Steele
Millions of people turn to Google Search each day for information on things as diverse as new cars or flu symptoms. The terms that they enter contain valuable information on their…
Q-Match: Self-Supervised Learning by Matching Distributions Induced by a Queue
Thomas Mulc, Debidatta Dwibedi
In semi-supervised learning, student-teacher distribution matching has been successful in improving performance of models using unlabeled data in conjunction with few labeled sampl…
CSS10: A Collection of Single Speaker Speech Datasets for 10 Languages
Kyubyong Park, Thomas Mulc
We describe our development of CSS10, a collection of single speaker speech datasets for ten languages. It is composed of short audio clips from LibriVox audiobooks and their align…