Syrine Krichene
Syrine Krichene is at Google Research Zurich, where she works on developing efficient systems for NLP and Sequential Question Answering. Prior to joining Google, Syrine worked as a machine learning researcher at Criteo, on optimization and recommender systems, and as a visiting scholar at UC Berkeley where she worked on optimization and game theory.
Syrine obtained her BS and MS degrees in Applied Mathematics and Computer Science from INP-ENSIMAG France.
Research Areas
Authored Publications
Sort By
Google
MatCha: Enhancing Visual Language Pretraining with Math Reasoning and Chart Derendering
Chenxi Pang
Mandar Joshi
Nigel Collier
Under review (2022)
DePlot: One-shot visual language understanding by plot-to-text translation
Chenxi Pang
Mandar Joshi
Nigel Collier
Under review (2022)
Table-To-Text generation and pre-training with TabT5
Ewa Andrejczuk
Findings of EMNLP (2022)
DoT: An efficient Double Transformer for NLP tasks with tables
Thomas Müller
Findings of the Association for Computational Linguistics: ACL 2021
TAPAS at SemEval-2021 Task 9: Reasoning over tables with intermediate pre-training
Thomas Müller
Proceedings of the Fifteenth Workshop on Semantic Evaluation (2021)
