György Szarvas

Researcher, Amazon Development Center Germany

Joined

January 2022

Names

György Szarvas (Preferred)

Emails

****@gmaill.com (Confirmed)

****@gmail.com (Confirmed)

****@amazon.com (Confirmed)

****@amazon.de (Confirmed)

Personal Links

Career & Education History

Researcher

Amazon Development Center Germany (amazon.de)

2013 – Present

Researcher

Nuance Communications (nuance.com)

2012 – 2013

Postdoc

Technische Universität Darmstadt (tu-darmstadt.de)

2009 – 2012

PhD student

University of Szeged (u-szeged.hu)

2004 – 2009

Advisors, Relations & Conflicts

No relations added

Expertise

Information Extraction

Present

Lexical Semantics

Present

Conversational AI

Present

Publications

Few Shot Rationale Generation using Self-Training with Dual Teachers
Aditya Srikanth Veerubhotla, Lahari Poddar, Jun Yin, György Szarvas, Sharanya Eswaran
- Published: 01 Jan 2023, Last Modified: 14 Dec 2023
- ACL (Findings) 2023
- Readers: Everyone
Transformer Uncertainty Estimation with Hierarchical Stochastic Attention
Jiahuan Pei, Cheng Wang, György Szarvas
- Published: 01 Jan 2022, Last Modified: 14 May 2023
- AAAI 2022
- Readers: Everyone
Calibrating Imbalanced Classifiers with Focal Loss: An Empirical Study
Cheng Wang, Jorge Balazs, György Szarvas, Patrick Ernst, Lahari Poddar, Pavel Danchenko
- Published: 01 Jan 2022, Last Modified: 14 May 2023
- EMNLP (Industry Track) 2022
- Readers: Everyone
Deploying a Retrieval based Response Model for Task Oriented Dialogues
Lahari Poddar, György Szarvas, Cheng Wang, Jorge Balazs, Pavel Danchenko, Patrick Ernst
- Published: 01 Jan 2022, Last Modified: 14 May 2023
- EMNLP (Industry Track) 2022
- Readers: Everyone
Transformer Uncertainty Estimation with Hierarchical Stochastic Attention
Jiahuan Pei, Cheng Wang, György Szarvas
- Published: 01 Jan 2021, Last Modified: 14 May 2023
- CoRR 2021
- Readers: Everyone
The Multilingual Amazon Reviews Corpus
Phillip Keung, Yichao Lu, György Szarvas, Noah A. Smith
- 2020 (modified: 21 Apr 2023)
- EMNLP (1) 2020
- Readers: Everyone
A Probabilistic Framework for Learning Domain Specific Hierarchical Word Embeddings
Lahari Poddar, György Szarvas, Lea Frermann
- 2019 (modified: 23 Oct 2021)
- CoRR 2019
- Readers: Everyone
Inducing Semantic Micro-Clusters from Deep Multi-View Representations of Novels
Lea Frermann, György Szarvas
- 2017 (modified: 16 Jul 2019)
- EMNLP 2017
- Readers: Everyone
Supervised All-Words Lexical Substitution using Delexicalized Features
György Szarvas, Chris Biemann, Iryna Gurevych
- 2013 (modified: 16 Jul 2019)
- HLT-NAACL 2013
- Readers: Everyone
Learning to Rank Lexical Substitutions
György Szarvas, Róbert Busa-Fekete, Eyke Hüllermeier
- 2013 (modified: 16 Jul 2019)
- EMNLP 2013
- Readers: Everyone

View all 20 publications

Co-Authors

View all 27 co-authors