Artem Sokolov

Also published as: Artem Sokokov


pdf bib
Improving End-to-End Speech Translation by Imitation-Based Knowledge Distillation with Synthetic Transcripts
Rebekka Hubert | Artem Sokolov | Stefan Riezler
Proceedings of the 20th International Conference on Spoken Language Translation (IWSLT 2023)

End-to-end automatic speech translation (AST) relies on data that combines audio inputs with text translation outputs. Previous work used existing large parallel corpora of transcriptions and translations in a knowledge distillation (KD) setup to distill a neural machine translation (NMT) into an AST student model. While KD allows using larger pretrained models, the reliance of previous KD approaches on manual audio transcripts in the data pipeline restricts the applicability of this framework to AST. We present an imitation learning approach where a teacher NMT system corrects the errors of an AST student without relying on manual transcripts. We show that the NMT teacher can recover from errors in automatic transcriptions and is able to correct erroneous translations of the AST student, leading to improvements of about 4 BLEU points over the standard AST end-to-end baseline on the English-German CoVoST-2 and MuST-C datasets, respectively. Code and data are publicly available:

pdf bib
Make Every Example Count: On the Stability and Utility of Self-Influence for Learning from Noisy NLP Datasets
Irina Bejan | Artem Sokolov | Katja Filippova
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

Increasingly larger datasets have become a standard ingredient to advancing the state-of-the-art in NLP. However, data quality might have already become the bottleneck to unlock further gains. Given the diversity and the sizes of modern datasets, standard data filtering is not straight-forward to apply, because of the multifacetedness of the harmful data and elusiveness of filtering rules that would generalize across multiple tasks. We study the fitness of task-agnostic self-influence scores of training examples for data cleaning, analyze their efficacy in capturing naturally occurring outliers, and investigate to what extent self-influence based data cleaning can improve downstream performance in machine translation, question answering and text classification, building up on recent approaches to self-influence calculation and automated curriculum learning.


pdf bib
Quality at a Glance: An Audit of Web-Crawled Multilingual Datasets
Julia Kreutzer | Isaac Caswell | Lisa Wang | Ahsan Wahab | Daan van Esch | Nasanbayar Ulzii-Orshikh | Allahsera Tapo | Nishant Subramani | Artem Sokolov | Claytone Sikasote | Monang Setyawan | Supheakmungkol Sarin | Sokhar Samb | Benoît Sagot | Clara Rivera | Annette Rios | Isabel Papadimitriou | Salomey Osei | Pedro Ortiz Suarez | Iroro Orife | Kelechi Ogueji | Andre Niyongabo Rubungo | Toan Q. Nguyen | Mathias Müller | André Müller | Shamsuddeen Hassan Muhammad | Nanda Muhammad | Ayanda Mnyakeni | Jamshidbek Mirzakhalov | Tapiwanashe Matangira | Colin Leong | Nze Lawson | Sneha Kudugunta | Yacine Jernite | Mathias Jenny | Orhan Firat | Bonaventure F. P. Dossou | Sakhile Dlamini | Nisansa de Silva | Sakine Çabuk Ballı | Stella Biderman | Alessia Battisti | Ahmed Baruwa | Ankur Bapna | Pallavi Baljekar | Israel Abebe Azime | Ayodele Awokoya | Duygu Ataman | Orevaoghene Ahia | Oghenefego Ahia | Sweta Agrawal | Mofetoluwa Adeyemi
Transactions of the Association for Computational Linguistics, Volume 10

With the success of large-scale pre-training and multilingual modeling in Natural Language Processing (NLP), recent years have seen a proliferation of large, Web-mined text datasets covering hundreds of languages. We manually audit the quality of 205 language-specific corpora released with five major public datasets (CCAligned, ParaCrawl, WikiMatrix, OSCAR, mC4). Lower-resource corpora have systematic issues: At least 15 corpora have no usable text, and a significant fraction contains less than 50% sentences of acceptable quality. In addition, many are mislabeled or use nonstandard/ambiguous language codes. We demonstrate that these issues are easy to detect even for non-proficient speakers, and supplement the human audit with automatic analyses. Finally, we recommend techniques to evaluate and improve multilingual corpora and discuss potential risks that come with low-quality data releases.


pdf bib
Bandits Don’t Follow Rules: Balancing Multi-Facet Machine Translation with Multi-Armed Bandits
Julia Kreutzer | David Vilar | Artem Sokolov
Findings of the Association for Computational Linguistics: EMNLP 2021

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 different levels of quality or complexity. Naturally, these facets do not occur with equal frequency, nor are they equally important for the test scenario at hand. In this work, we propose to optimize this balance jointly with MT model parameters to relieve system developers from manual schedule design. A multi-armed bandit is trained to dynamically choose between facets in a way that is most beneficial for the MT system. We evaluate it on three different multi-facet applications: balancing translationese and natural training data, or data from multiple domains or multiple language pairs. We find that bandit learning leads to competitive MT systems across tasks, and our analysis provides insights into its learned strategies and the underlying data sets.

pdf bib
Controlling Machine Translation for Multiple Attributes with Additive Interventions
Andrea Schioppa | David Vilar | Artem Sokolov | Katja Filippova
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

Fine-grained control of machine translation (MT) outputs along multiple attributes is critical for many modern MT applications and is a requirement for gaining users’ trust. A standard approach for exerting control in MT is to prepend the input with a special tag to signal the desired output attribute. Despite its simplicity, attribute tagging has several drawbacks: continuous values must be binned into discrete categories, which is unnatural for certain applications; interference between multiple tags is poorly understood. We address these problems by introducing vector-valued interventions which allow for fine-grained control over multiple attributes simultaneously via a weighted linear combination of the corresponding vectors. For some attributes, our approach even allows for fine-tuning a model trained without annotations to support such interventions. In experiments with three attributes (length, politeness and monotonicity) and two language pairs (English to German and Japanese) our models achieve better control over a wider range of tasks compared to tagging, and translation quality does not degrade when no control is requested. Finally, we demonstrate how to enable control in an already trained model after a relatively cheap fine-tuning stage.

pdf bib
Don’t Search for a Search Method — Simple Heuristics Suffice for Adversarial Text Attacks
Nathaniel Berger | Stefan Riezler | Sebastian Ebert | Artem Sokolov
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

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 search algorithms and search constraints, accompanied by benchmark algorithms and tasks. We implement an algorithm inspired by zeroth order optimization-based attacks and compare with the benchmark results in the TextAttack framework. Surprisingly, we find that optimization-based methods do not yield any improvement in a constrained setup and slightly benefit from approximate gradient information only in unconstrained setups where search spaces are larger. In contrast, simple heuristics exploiting nearest neighbors without querying the target function yield substantial success rates in constrained setups, and nearly full success rate in unconstrained setups, at an order of magnitude fewer queries. We conclude from these results that current TextAttack benchmark tasks are too easy and constraints are too strict, preventing meaningful research on black-box adversarial text attacks.


pdf bib
The Sockeye Neural Machine Translation Toolkit at AMTA 2018
Felix Hieber | Tobias Domhan | Michael Denkowski | David Vilar | Artem Sokolov | Ann Clifton | Matt Post
Proceedings of the 13th Conference of the Association for Machine Translation in the Americas (Volume 1: Research Track)

pdf bib
Learning to Segment Inputs for NMT Favors Character-Level Processing
Julia Kreutzer | Artem Sokolov
Proceedings of the 15th International Conference on Spoken Language Translation

Most modern neural machine translation (NMT) systems rely on presegmented inputs. Segmentation granularity importantly determines the input and output sequence lengths, hence the modeling depth, and source and target vocabularies, which in turn determine model size, computational costs of softmax normalization, and handling of out-of-vocabulary words. However, the current practice is to use static, heuristic-based segmentations that are fixed before NMT training. This begs the question whether the chosen segmentation is optimal for the translation task. To overcome suboptimal segmentation choices, we present an algorithm for dynamic segmentation, that is trainable end-to-end and driven by the NMT objective. In an evaluation on four translation tasks we found that, given the freedom to navigate between different segmentation levels, the model prefers to operate on (almost) character level, providing support for purely character-level NMT models from a novel angle.


pdf bib
A Shared Task on Bandit Learning for Machine Translation
Artem Sokolov | Julia Kreutzer | Kellen Sunderland | Pavel Danchenko | Witold Szymaniak | Hagen Fürstenau | Stefan Riezler
Proceedings of the Second Conference on Machine Translation

pdf bib
Bandit Structured Prediction for Neural Sequence-to-Sequence Learning
Julia Kreutzer | Artem Sokolov | Stefan Riezler
Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Bandit structured prediction describes a stochastic optimization framework where learning is performed from partial feedback. This feedback is received in the form of a task loss evaluation to a predicted output structure, without having access to gold standard structures. We advance this framework by lifting linear bandit learning to neural sequence-to-sequence learning problems using attention-based recurrent neural networks. Furthermore, we show how to incorporate control variates into our learning algorithms for variance reduction and improved generalization. We present an evaluation on a neural machine translation task that shows improvements of up to 5.89 BLEU points for domain adaptation from simulated bandit feedback.

pdf bib
Counterfactual Learning from Bandit Feedback under Deterministic Logging : A Case Study in Statistical Machine Translation
Carolin Lawrence | Artem Sokolov | Stefan Riezler
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing

The goal of counterfactual learning for statistical machine translation (SMT) is to optimize a target SMT system from logged data that consist of user feedback to translations that were predicted by another, historic SMT system. A challenge arises by the fact that risk-averse commercial SMT systems deterministically log the most probable translation. The lack of sufficient exploration of the SMT output space seemingly contradicts the theoretical requirements for counterfactual learning. We show that counterfactual learning from deterministic bandit logs is possible nevertheless by smoothing out deterministic components in learning. This can be achieved by additive and multiplicative control variates that avoid degenerate behavior in empirical risk minimization. Our simulation experiments show improvements of up to 2 BLEU points by counterfactual learning from deterministic bandit feedback.


pdf bib
Learning Structured Predictors from Bandit Feedback for Interactive NLP
Artem Sokolov | Julia Kreutzer | Christopher Lo | Stefan Riezler
Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)


pdf bib
A Coactive Learning View of Online Structured Prediction in Statistical Machine Translation
Artem Sokolov | Stefan Riezler | Shay B. Cohen
Proceedings of the Nineteenth Conference on Computational Natural Language Learning

pdf bib
Bandit structured prediction for learning from partial feedback in statistical machine translation
Artem Sokolov | Stefan Riezler | Tanguy Urvoy
Proceedings of Machine Translation Summit XV: Papers


pdf bib
Learning Translational and Knowledge-based Similarities from Relevance Rankings for Cross-Language Retrieval
Shigehiko Schamoni | Felix Hieber | Artem Sokolov | Stefan Riezler
Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)


pdf bib
Boosting Cross-Language Retrieval by Learning Bilingual Phrase Associations from Relevance Rankings
Artem Sokokov | Laura Jehl | Felix Hieber | Stefan Riezler
Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing


pdf bib
Computing Lattice BLEU Oracle Scores for Machine Translation
Artem Sokolov | Guillaume Wisniewski | François Yvon
Proceedings of the 13th Conference of the European Chapter of the Association for Computational Linguistics

pdf bib
Hai-Son Le | Thomas Lavergne | Alexandre Allauzen | Marianna Apidianaki | Li Gong | Aurélien Max | Artem Sokolov | Guillaume Wisniewski | François Yvon
Proceedings of the Seventh Workshop on Statistical Machine Translation

pdf bib
WSD for n-best reranking and local language modeling in SMT
Marianna Apidianaki | Guillaume Wisniewski | Artem Sokolov | Aurélien Max | François Yvon
Proceedings of the Sixth Workshop on Syntax, Semantics and Structure in Statistical Translation

pdf bib
LIMSI: Learning Semantic Similarity by Selecting Random Word Subsets
Artem Sokolov
*SEM 2012: The First Joint Conference on Lexical and Computational Semantics – Volume 1: Proceedings of the main conference and the shared task, and Volume 2: Proceedings of the Sixth International Workshop on Semantic Evaluation (SemEval 2012)

pdf bib
Non-linear n-best List Reranking with Few Features
Artem Sokolov | Guillaume Wisniewski | François Yvon
Proceedings of the 10th Conference of the Association for Machine Translation in the Americas: Research Papers

In Machine Translation, it is customary to compute the model score of a predicted hypothesis as a linear combination of multiple features, where each feature assesses a particular facet of the hypothesis. The choice of a linear combination is usually justified by the possibility of efficient inference (decoding); yet, the appropriateness of this simple combination scheme to the task at hand is rarely questioned. In this paper, we propose an approach that replaces the linear scoring function with a non-linear scoring function. To investigate the applicability of this approach, we rescore n-best lists generated with a conventional machine translation engine (using a linear scoring function for generating its hypotheses) with a non-linear scoring function learned using the learning-to-rank framework. Moderate, though consistent, gains in BLEU are demonstrated on the WMT’10, WMT’11 and WMT’12 test sets.

pdf bib
Workshop on Monolingual Machine Translation
Tsuyoshi Okita | Artem Sokolov | Taro Watanabe
Workshop on Monolingual Machine Translation


pdf bib
Advances on spoken language translation in the Quaero program
Karim Boudahmane | Bianka Buschbeck | Eunah Cho | Josep Maria Crego | Markus Freitag | Thomas Lavergne | Hermann Ney | Jan Niehues | Stephan Peitz | Jean Senellart | Artem Sokolov | Alex Waibel | Tonio Wandmacher | Joern Wuebker | François Yvon
Proceedings of the 8th International Workshop on Spoken Language Translation: Evaluation Campaign

The Quaero program is an international project promoting research and industrial innovation on technologies for automatic analysis and classification of multimedia and multilingual documents. Within the program framework, research organizations and industrial partners collaborate to develop prototypes of innovating applications and services for access and usage of multimedia data. One of the topics addressed is the translation of spoken language. Each year, a project-internal evaluation is conducted by DGA to monitor the technological advances. This work describes the design and results of the 2011 evaluation campaign. The participating partners were RWTH, KIT, LIMSI and SYSTRAN. Their approaches are compared on both ASR output and reference transcripts of speech data for the translation between French and German. The results show that the developed techniques further the state of the art and improve translation quality.

pdf bib
Alexandre Allauzen | Hélène Bonneau-Maynard | Hai-Son Le | Aurélien Max | Guillaume Wisniewski | François Yvon | Gilles Adda | Josep Maria Crego | Adrien Lardilleux | Thomas Lavergne | Artem Sokolov
Proceedings of the Sixth Workshop on Statistical Machine Translation

pdf bib
Minimum Error Rate Training Semiring
Artem Sokolov | François Yvon
Proceedings of the 15th Annual Conference of the European Association for Machine Translation