no code implementations • 19 Aug 2022 • Soham Deshmukh, Charles Lee
Additionally, the modular nature of the proposed framework allows plug-and-play for any future developments in both pre-trained language and task-oriented dialogue models.
no code implementations • 17 Nov 2021 • Joaquin Delgado Fernandez, Sergio Potenciano Menci, Charles Lee, Gilbert Fridgen
This paper investigates how these requirements can be addressed through a combination of federated learning and privacy preserving techniques such as differential privacy and secure aggregation.
no code implementations • 5 Oct 2021 • Ruijie Zhou, Soham Deshmukh, Jeremiah Greer, Charles Lee
Current research in dialogue systems is focused on conversational assistants working on short conversations in either task-oriented or open domain settings.
no code implementations • EMNLP 2020 • Barun Patra, Chala Fufa, Pamela Bhattacharya, Charles Lee
State of the art research for date-time entity extraction from text is task agnostic.
no code implementations • COLING 2020 • Vishwas Suryanarayanan, Barun Patra, Pamela Bhattacharya, Chala Fufa, Charles Lee
Intelligent assistants like Cortana, Siri, Alexa, and Google Assistant are trained to parse information when the conversation is synchronous and short; however, for email-based conversational agents, the communication is asynchronous, and often contains information irrelevant to the assistant.
no code implementations • NeurIPS 2008 • Michael P. Holmes, Jr. Isbell, Charles Lee, Alexander G. Gray
The Singular Value Decomposition is a key operation in many machine learning methods.