no code implementations • 23 Oct 2023 • Ankita Bhaumik, Praveen Venkateswaran, Yara Rizk, Vatche Isahagian
The popularity of conversational digital assistants has resulted in the availability of large amounts of conversational data which can be utilized for improved user experience and personalized response generation.
no code implementations • 6 Dec 2022 • Praveen Venkateswaran, Evelyn Duesterwald, Vatche Isahagian
Dialogue State Tracking (DST), a key component of task-oriented conversation systems, represents user intentions by determining the values of pre-defined slots in an ongoing dialogue.
no code implementations • 3 Nov 2022 • Praveen Venkateswaran, Vatche Isahagian, Vinod Muthusamy, Nalini Venkatasubramanian
Existing federated learning models that follow the standard risk minimization paradigm of machine learning often fail to generalize in the presence of spurious correlations in the training data.
no code implementations • 26 Oct 2022 • Yara Rizk, Praveen Venkateswaran, Vatche Isahagian, Vinod Muthusamy
The inception of large language models has helped advance state-of-the-art performance on numerous natural language tasks.