Conversational Agent
Conversational agents, or chatbots, aim to create AI systems capable of engaging in natural, human-like dialogue to accomplish various tasks. Current research emphasizes improving long-term memory, context understanding, and the ability to handle complex, multi-turn conversations, often employing large language models (LLMs) and retrieval-augmented generation (RAG) techniques. These advancements are driving progress in diverse applications, including customer service, education, and even creative fields like theatre, while also raising important ethical considerations regarding safety, bias, and user interaction.
Papers
Metric Learning and Adaptive Boundary for Out-of-Domain Detection
Petr Lorenc, Tommaso Gargiani, Jan Pichl, Jakub Konrád, Petr Marek, Ondřej Kobza, Jan Šedivý
Detecting early signs of depression in the conversational domain: The role of transfer learning in low-resource scenarios
Petr Lorenc, Ana-Sabina Uban, Paolo Rosso, Jan Šedivý
The Moral Integrity Corpus: A Benchmark for Ethical Dialogue Systems
Caleb Ziems, Jane A. Yu, Yi-Chia Wang, Alon Halevy, Diyi Yang
Global Readiness of Language Technology for Healthcare: What would it Take to Combat the Next Pandemic?
Ishani Mondal, Kabir Ahuja, Mohit Jain, Jacki O Neil, Kalika Bali, Monojit Choudhury