
Balint Miklos
Balint is a tech lead on Google Lens working on image and text based classification and content generation systems. He lead the development of Multisearch, a search quality system to produce relevant results based on image and text signals, i.e. multimodal search.
In the past, he also lead the development of punctuation prediction systems for speech recognition as part of Google Assistant org.
Previously, Balint was leading for 8+ years a group in Gmail and Workspace to build magical user experiences using machine learning. Among others he lead the development of Smart Reply in Gmail, email classifiers to Promotional, Social, etc. and advised and mentored the leads of the projects Smart Compose and Spelling and Grammar suggestions in Gmail and Google Docs. Balint earned his PhD in computer science from ETH Zurich in 2010.
Authored Publications
Sort By
Google
REPLACING HUMAN-RECORDED AUDIO WITH SYNTHETIC AUDIOFOR ON-DEVICE UNSPOKEN PUNCTUATION PREDICTION
Bogdan Prisacari
Daria Soboleva
Felix Weissenberger
Justin Lu
Márius Šajgalík
ICASSP 2021: International Conference on Acoustics, Speech and Signal Processing (2021) (to appear)
Efficient Natural Language Response Suggestion for Smart Reply
Matthew Henderson
Rami Al-Rfou
Brian Strope
László Lukács
Ray Kurzweil
ArXiv e-prints (2017)
Template Induction over Unstructured Email Corpora
Lluís Garcia-Pueyo
Ivo Krka
Tobias Kaufmann
Proc. of the 26th International World Wide Web Conference (2017), pp. 1521-1530
Hierarchical Label Propagation and Discovery for Machine Generated Email
Lluis Garcia-Pueyo
Vanja Josifovski
Ivo Krka
Amitabh Saikia
Jie Yang
Sujith Ravi
Proceedings of the International Conference on Web Search and Data Mining (WSDM), ACM (2016), pp. 317-326
Smart Reply: Automated Response Suggestion for Email
Karol Kurach
Sujith Ravi
Tobias Kaufman
Laszlo Lukacs
Peter Young
Vivek Ramavajjala
Proceedings of the ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) (2016).