Ansel MacLaughlin — accepted AI-conference papers

2023

Self-Healing Through Error Detection, Attribution, and Retraining

Ansel MacLaughlin, Anna Rumshisky, Rinat Khaziev, Anil Ramakrishna, Yuval Merhav, Rahul Gupta

ICASSP 2023accepted

Negative feedback received from users of voice agents can provide valuable training signal to their underlying ML systems. However, such systems tend to have complex inference pipelines consisting of multiple model-based and deterministic components. Therefore, when negative feedback is received, it…

Cited by 0 Source ↗Scholar ↗

2022

Federated Learning with Noisy User Feedback

Rahul Sharma, Anil Ramakrishna, Ansel MacLaughlin, Anna Rumshisky, Jimit Majmudar, Clement Chung +2

NAACL 2022long

Machine Learning (ML) systems are getting increasingly popular, and drive more and more applications and services in our daily life. Thishas led to growing concerns over user privacy, since human interaction data typically needs to be transmitted to the cloud in order to trainand improve such system…

Cited by 14 Source ↗PDF ↗Scholar ↗