activity
20172021
most citedDon't Search for a Search Method -- Simple Heuristics Suffice for Adversarial Text Attacks

1 citations · 2 across the 4 of their papers we have counts for

collaborators

8 papers

cs.CL2021

Bandits Don't Follow Rules: Balancing Multi-Facet Machine Translation with Multi-Armed Bandits

Julia Kreutzer, David Vilar, Artem Sokolov

Training data for machine translation (MT) is often sourced from a multitude of large corpora that are multi-faceted in nature, e.g. containing contents from multiple domains or di…

cs.CL20211 cited

Don't Search for a Search Method -- Simple Heuristics Suffice for Adversarial Text Attacks

Nathaniel Berger, Stefan Riezler, Artem Sokolov +1

Recently more attention has been given to adversarial attacks on neural networks for natural language processing (NLP). A central research topic has been the investigation of searc…

cs.CL20211 cited

Fixing exposure bias with imitation learning needs powerful oracles

Luca Hormann, Artem Sokolov

We apply imitation learning (IL) to tackle the NMT exposure bias problem with error-correcting oracles, and evaluate an SMT lattice-based oracle which, despite its excellent perfor…

stat.ML2020

Sparse Perturbations for Improved Convergence in Stochastic Zeroth-Order Optimization

Mayumi Ohta, Nathaniel Berger, Artem Sokolov +1

Interest in stochastic zeroth-order (SZO) methods has recently been revived in black-box optimization scenarios such as adversarial black-box attacks to deep neural networks. SZO m…

cs.CL2018

Learning to Segment Inputs for NMT Favors Character-Level Processing

Julia Kreutzer, Artem Sokolov

Most modern neural machine translation (NMT) systems rely on presegmented inputs. Segmentation granularity importantly determines the input and output sequence lengths, hence the m…

stat.ML2018

Sparse Stochastic Zeroth-Order Optimization with an Application to Bandit Structured Prediction

Artem Sokolov, Julian Hitschler, Mayumi Ohta +1

Stochastic zeroth-order (SZO), or gradient-free, optimization allows to optimize arbitrary functions by relying only on function evaluations under parameter perturbations, however,…