Michael Heck
Scholar

Michael Heck

Google Scholar ID: uahwB_IAAAAJ
Heinrich Heine University Düsseldorf, Germany
Automatic speech recognitionUnsupervised learningRepresentation learningNatural language processingDialog systems
Citations & Impact
All-time
Citations
769
 
H-index
13
 
i10-index
16
 
Publications
20
 
Co-authors
15
list available
Resume (English only)
Academic Achievements
  • - Publications:
  • - “Learning from Noisy Labels via Self-Taught On-the-Fly Meta Loss Rescaling,” AAAI'25
  • - “ChatGPT for Zero-shot Dialogue State Tracking: A Solution or an Opportunity?” ACL 2023
  • - “Explaining the Sensation: An Accessible Introduction to ChatGPT,” HeiCAD Special Event
  • - “Towards Adaptive and Evolving Task-oriented Dialogue Systems,” Invited Talk 2021
  • - “Out-of-Task Training for Dialog State Tracking Models,” COLING 2020
  • - “TripPy: A Triple Copy Strategy for Value Independent Neural Dialog State Tracking,” SIGDIAL 2020
Research Experience
  • - Member of the Dialog Systems and Machine Learning Group at Heinrich Heine University Düsseldorf, working with Milica Gašić
  • - Technical Staff at RIKEN Center for Advanced Intelligence Project (AIP), Tourism Information Analytics (TIA) Team, Japan, from 2018 to 2019
Education
  • - Doctor of Engineering (D.Eng.), 2018, Nara Institute of Science and Technology (NAIST), Japan
  • - Supervisors: Satoshi Nakamura and Sakriani Sakti
  • - Research areas: Acoustic modeling, unsupervised learning, representation learning, etc.
  • - Diploma in Informatics (Dipl.-Inform.), Karlsruhe Institute of Technology (KIT), Germany
  • - Supervisors: Alex Waibel and Sebastian Stüker
Background
  • - Natural language processing researcher
  • - Background: Automatic speech recognition
  • - Current focus: Dialogue systems, dialogue state tracking
  • - Research interests: Representation learning in the context of dialogue systems
Miscellany
  • Contact: michael [dot] heck [at] hhu [dot] de
  • Address: Universitätsstr. 1 Building 25.12, Düsseldorf, Germany 40225