Martin Szummer
Scholar

Martin Szummer

Google Scholar ID: w-hJ1BoAAAAJ
DeepMind
machine learningcausal inferencerobust machine learningnatural language processing
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
805
 
H-index
16
 
i10-index
23
 
Publications
20
 
Co-authors
0
 
Contact
LinkedInOpen ↗
Resume
Academic Achievements
  • Published numerous papers, including 'POMDP-based dialogue manager adaptation to extended domains' which won the Best Paper Award at SIGDIAL 2013.
Research Experience
  • Currently a researcher at the University of Cambridge, part of the Spoken Dialogue Systems group. Previously, he was a researcher at Microsoft Research in Cambridge, in the machine learning and perception group.
Education
  • Ph.D. in machine learning from MIT in 2002; M.S. degree from the MIT Media Lab.
Background
  • Research interests include deep learning and flexible models, improving user interaction, learning the semantics of natural language, methods to control overfitting, structured prediction, probabilistic programming, and big data.
Miscellany
  • Applications include text mining and language understanding, image recognition and search, handwriting recognition, user behavior modeling from clicks and browsing data, and computational advertising.