Dialogue systems learn new words with fewer questions
Reports and Proceedings
Updates every hour. Last Updated: 15-Dec-2025 12:11 ET (15-Dec-2025 17:11 GMT/UTC)
The University of Osaka researchers developed a reinforcement learning framework that lets dialogue systems efficiently learn new words while asking fewer questions. This approach enhances user experience and enables future systems to naturally acquire family-specific nicknames and expressions, becoming more familiar companions in everyday life.
Research has opened the door for coastal wetland restoration projects to potentially earn tradeable biodiversity certificates.
A groundbreaking new study from the Alliance for Clinical Trials in Oncology aims to test whether digital tools and chatbot technology can help young adult cancer survivors get the genetic counseling they need to better understand future health risks to themselves and family members.
A new artificial intelligence tool can scan social media data to discover adverse events associated with consumer health products, according to a study published September 30th in the open-access journal PLOS Digital Health by John Ayers of the University of California, San Diego, U.S., and colleagues.