Jack Goetz
YOU?
Author Swipe
View article: Towards Zero-Shot Frame Semantic Parsing with Task Agnostic Ontologies and Simple Labels
Towards Zero-Shot Frame Semantic Parsing with Task Agnostic Ontologies and Simple Labels Open
Frame semantic parsing is an important component of task-oriented dialogue systems. Current models rely on a significant amount training data to successfully identify the intent and slots in the user's input utterance. This creates a signi…
View article: Towards Zero-Shot Frame Semantic Parsing with Task Agnostic Ontologies and Simple Labels
Towards Zero-Shot Frame Semantic Parsing with Task Agnostic Ontologies and Simple Labels Open
Danilo Neves Ribeiro, Jack Goetz, Omid Abdar, Mike Ross, Annie Dong, Kenneth Forbus, Ahmed Mohamed. Proceedings of the 2nd Workshop on Pattern-based Approaches to NLP in the Age of Deep Learning. 2023.
View article: FedSynth: Gradient Compression via Synthetic Data in Federated Learning
FedSynth: Gradient Compression via Synthetic Data in Federated Learning Open
Model compression is important in federated learning (FL) with large models to reduce communication cost. Prior works have been focusing on sparsification based compression that could desparately affect the global model accuracy. In this w…
View article: AutoNLU: Detecting, root-causing, and fixing NLU model errors
AutoNLU: Detecting, root-causing, and fixing NLU model errors Open
Improving the quality of Natural Language Understanding (NLU) models, and more specifically, task-oriented semantic parsing models, in production is a cumbersome task. In this work, we present a system called AutoNLU, which we designed to …
View article: Learning From Others Without Sacrificing Privacy: Simulation Comparing Centralized and Federated Machine Learning on Mobile Health Data
Learning From Others Without Sacrificing Privacy: Simulation Comparing Centralized and Federated Machine Learning on Mobile Health Data Open
Background The use of wearables facilitates data collection at a previously unobtainable scale, enabling the construction of complex predictive models with the potential to improve health. However, the highly personal nature of these data …
View article: Mining events with declassified diplomatic documents
Mining events with declassified diplomatic documents Open
Since 1973, the U.S. State Department has been using electronic record systems to preserve classified communications. Recently, approximately 1.9 million of these records from 1973–77 have been made available by the U.S. National Archives.…
View article: Learning From Others Without Sacrificing Privacy: Simulation Comparing Centralized and Federated Machine Learning on Mobile Health Data (Preprint)
Learning From Others Without Sacrificing Privacy: Simulation Comparing Centralized and Federated Machine Learning on Mobile Health Data (Preprint) Open
BACKGROUND The use of wearables facilitates data collection at a previously unobtainable scale, enabling the construction of complex predictive models with the potential to improve health. However, the highly personal nature of these data…
View article: Federated Learning via Synthetic Data
Federated Learning via Synthetic Data Open
Federated learning allows for the training of a model using data on multiple clients without the clients transmitting that raw data. However the standard method is to transmit model parameters (or updates), which for modern neural networks…
View article: What Does the Machine Learn? Knowledge Representations of Chemical Reactivity
What Does the Machine Learn? Knowledge Representations of Chemical Reactivity Open
In a departure from conventional chemical approaches, data-driven models of chemical reactions have recently been shown to be statistically successful using machine learning. These models, however, are largely black box in character and ha…
View article: Not All are Made Equal: Consistency of Weighted Averaging Estimators Under Active Learning
Not All are Made Equal: Consistency of Weighted Averaging Estimators Under Active Learning Open
Active learning seeks to build the best possible model with a budget of labelled data by sequentially selecting the next point to label. However the training set is no longer \textit{iid}, violating the conditions required by existing cons…
View article: Active Federated Learning
Active Federated Learning Open
Federated Learning allows for population level models to be trained without centralizing client data by transmitting the global model to clients, calculating gradients locally, then averaging the gradients. Downloading models and uploading…
View article: Federated User Representation Learning
Federated User Representation Learning Open
Collaborative personalization, such as through learned user representations (embeddings), can improve the prediction accuracy of neural-network-based models significantly. We propose Federated User Representation Learning (FURL), a simple,…
View article: Mining Events with Declassified Diplomatic Documents
Mining Events with Declassified Diplomatic Documents Open
Since 1973 the State Department has been using electronic records systems to preserve classified communications. Recently, approximately 1.9 million of these records from 1973-77 have been made available by the U.S. National Archives. Whil…
View article: Online Multiclass Boosting
Online Multiclass Boosting Open
Recent work has extended the theoretical analysis of boosting algorithms to multiclass problems and to online settings. However, the multiclass extension is in the batch setting and the online extensions only consider binary classification…