My research centers around creating an intelligent Human-Computer Interaction that is adaptive and affect-sensitive.
I'm currently working as postdoctoral researcher with Milica Gašić at Dialog Systems and Machine Learning Group at Heinrich Heine University Düsseldorf, Germany. I'm particularly interested in optimizing dialogue policies for task-oriented systems using reinforcement learning methods without any predefined action space.
In the past I focused on empathetic dialogue and emotion elicitation in chat-based dialogue systems. During my master's and Ph.D. my supervisors were Satoshi Nakamura, Sakriani Sakti, and Koichiro Yoshino. I have also worked with Graham Neubig, Randy Gomez, Dessi Lestari, and Ayu Purwarianti.
December 2024
Our paper "Learning from Noisy Labels via Self-Taught On-the-Fly Meta Loss Rescaling" is accepted at AAAI 2025!
July 2024
Our paper "Affect Recognition in Conversations Using Large Language Models" is accepted at SIGDIAL 2024!
Our paper "Infusing Emotions into Task-oriented Dialogue Systems: Understanding, Management, and Generation" is accepted at SIGDIAL 2024!
July 2023
I gave an invited talk titled "Dialogue Evaluation via Offline Reinforcement Learning and Emotion Prediction" at NLP for Conversational AI 5 co-located at ACL 2023 in Toronto, Canada.
We presented two posters at ACL 2023 in Toronto, Canada.
Our paper "From Chatter to Matter: Addressing Critical Steps of Emotion Recognition Learning in Task-oriented Dialogue" is accepted at SIGDIAL 2023!
June 2023
I gave a keynote titled "Dialogue Evaluation via Offline Reinforcement Learning and Emotion Prediction" at the 32nd TaCoS Conference in Düsseldorf, Germany.
May 2023
Our paper "ChatGPT for Zero-shot Dialogue State Tracking: A Solution or an Opportunity?" is accepted at ACL 2023!
December 2022
Dialogue Evaluation with Offline RL
LAVA: Latent action spaces via variational auto-encoding
Universitätsstr. 1 Gebäude 25.12.01.34, Düsseldorf, Germany 40225