Ruprecht-Karls-Universität Heidelberg

Artem Sokolov

I am a research scientist at Google Berlin working on machine translation and other structured prediction problems for NLP. Simultaneously, I hold an honorary professor position at the Heidelberg University.

Before Google I was at Amazon and earlier at the Statistical NLP Group, lead by Prof. Stefan Riezler (where I'm still teaching ML courses), and even earlier at the LIMSI and the Orange Labs, R&D in France. I obtained a PhD in Computer Science and Artificial Intelligence from the IRTCITS research center in Kyiv for a thesis on randomized algorithms for locality-sensitive embeddings of the Levenstein edit distance.


Recent Publications

  1. I. Bejan, A. Sokolov, K. Filippova. Make Every Example Count: On the Stability and Utility of Self-Influence for Learning from Noisy NLP Datasets, Empirical Methods in Natural Language Processing (EMNLP), 2023 [ArXiv]
  2. A. Schioppa, P. Zablotskaia, D. Vilar, A. Sokolov Scaling Up Influence Functions, Association for the Advancement of Artificial Intelligence (AAAI), 2022, [poster]
  3. J. Kreutzer, D. Vilar, A. Sokolov. Bandits Don't Follow Rules: Balancing Multi-Facet Machine Translation with Multi-Armed Bandits, Empirical Methods in Natural Language Processing (EMNLP), 2021
  4. A. Schioppa, A. Sokolov, D. Vilar, K. Filippova. Controlling Machine Translation for Multiple Attributes with Additive Interventions, Empirical Methods in Natural Language Processing (EMNLP), 2021, [poster]
  5. N. Berger, S. Riezler, A. Sokolov, S. Ebert. Don't Search for a Search Method - Simple Heuristics Suffice for Adversarial Text Attacks, Empirical Methods in Natural Language Processing (EMNLP), 2021
  6. L. Hormann, A. Sokolov. Fixing exposure bias with imitation learning needs powerful oracles, 2021, [ArXiv]
  7. J. Kreutzer, A. Sokolov. Learning to Segment Inputs for NMT Favors Character-Level Processing, Int. Workshop on Spoken Language Translation (IWSLT), 2018 [extended report]
  8. F. Hieber, T. Domhan, M. Denkowski, D. Vilar, A. Sokolov, A. Clifton, M. Post. Sockeye: A Toolkit for Neural Machine Translation, American Machine Translation Association (AMTA), 2018 [complete ArXiv version] [code]
  9. C. Lawrence, A. Sokolov, S. Riezler. Counterfactual Learning from Bandit Feedback under Deterministic Logging: A Case Study in Statistical Machine Translation, Empirical Methods in Natural Language Processing (EMNLP), Copenhagen, Denmark, 2017 [poster]
  10. A. Sokolov, J. Kreutzer, K. Sunderland, P. Danchenko, W. Szymaniak, H. Fürstenau, S. Riezler. A Shared Task on Bandit Learning for Machine Translation, Conference on Machine Translation (WMT), Copenhagen, Denmark, 2017 [slides]
See the full list on the publication page.


Institut für Computerlinguistik,
Universität Heidelberg
Im Neuenheimer Feld 325, Room 107
69120 Heidelberg

E-mail sokolov(at)

Hobby - travel reports

Some of my trip accounts and travel articles (in ukrainian)
zum Seitenanfang