Aliaksei Severyn

67 papers A* 13A 2B 3Journal 29Unranked 19
YearRankTypeTitle / Venue / Authors
2025 A* conf
BOND: Aligning LLMs with Best-of-N Distillation.
ICLR
Pier Giuseppe Sessa, Robert Dadashi-Tazehozi, Léonard Hussenot, Johan Ferret, Nino Vieillard, Alexandre Ramé, Bobak Shahriari, Sarah Perrin, Abram L. Friesen, Geoffrey Cideron, Sertan Girgin, Piotr Stanczyk, Andrea Michi, Danila Sinopalnikov, Sabela Ramos Garea, Amélie Héliou, Aliaksei Severyn, Matthew Hoffman, Nikola Momchev, Olivier Bachem
2024 J jnl
BOND: Aligning LLMs with Best-of-N Distillation.
CoRR
Pier Giuseppe Sessa, Robert Dadashi, Léonard Hussenot, Johan Ferret, Nino Vieillard, Alexandre Ramé, Bobak Shahriari, Sarah Perrin, Abe Friesen, Geoffrey Cideron, Sertan Girgin, Piotr Stanczyk, Andrea Michi, Danila Sinopalnikov, Sabela Ramos, Amélie Héliou, Aliaksei Severyn, Matt Hoffman, Nikola Momchev, Olivier Bachem
2024 J jnl
Offline Regularised Reinforcement Learning for Large Language Models Alignment.
CoRR
Pierre Harvey Richemond, Yunhao Tang, Daniel Guo, Daniele Calandriello, Mohammad Gheshlaghi Azar, Rafael Rafailov, Bernardo Ávila Pires, Eugene Tarassov, Lucas Spangher, Will Ellsworth, Aliaksei Severyn, Jonathan Mallinson, Lior Shani, Gil Shamir, Rishabh Joshi, Tianqi Liu, Rémi Munos, Bilal Piot
2024 — conf
Small Language Models Improve Giants by Rewriting Their Outputs.
EACL (1)
Giorgos Vernikos, Arthur Brazinskas, Jakub Adámek, Jonathan Mallinson, Aliaksei Severyn, Eric Malmi
2024 J jnl
West-of-N: Synthetic Preference Generation for Improved Reward Modeling.
CoRR
Alizée Pace, Jonathan Mallinson, Eric Malmi, Sebastian Krause, Aliaksei Severyn
2023 A* conf
Fast Text Generation with Text-Editing Models.
KDD
Eric Malmi, Yue Dong, Jonathan Mallinson, Aleksandr Chuklin, Jakub Adámek, Daniil Mirylenka, Felix Stahlberg, Sebastian Krause, Shankar Kumar, Aliaksei Severyn
2023 J jnl
Small Language Models Improve Giants by Rewriting Their Outputs.
CoRR
Giorgos Vernikos, Arthur Brazinskas, Jakub Adámek, Jonathan Mallinson, Aliaksei Severyn, Eric Malmi
2023 — conf
Teaching Small Language Models to Reason.
ACL (2)
Lucie Charlotte Magister, Jonathan Mallinson, Jakub Adámek, Eric Malmi, Aliaksei Severyn
2022 — conf
EdiT5: Semi-Autoregressive Text Editing with T5 Warm-Start.
EMNLP (Findings)
Jonathan Mallinson, Jakub Adámek, Eric Malmi, Aliaksei Severyn
2022 J jnl
EdiT5: Semi-Autoregressive Text-Editing with T5 Warm-Start.
CoRR
Jonathan Mallinson, Jakub Adámek, Eric Malmi, Aliaksei Severyn
2022 J jnl
Teaching Small Language Models to Reason.
CoRR
Lucie Charlotte Magister, Jonathan Mallinson, Jakub Adámek, Eric Malmi, Aliaksei Severyn
2022 J jnl
Text Generation with Text-Editing Models.
CoRR
Eric Malmi, Yue Dong, Jonathan Mallinson, Aleksandr Chuklin, Jakub Adámek, Daniil Mirylenka, Felix Stahlberg, Sebastian Krause, Shankar Kumar, Aliaksei Severyn
2021 — conf
A Simple Recipe for Multilingual Grammatical Error Correction.
ACL/IJCNLP (2)
Sascha Rothe, Jonathan Mallinson, Eric Malmi, Sebastian Krause, Aliaksei Severyn
2021 J jnl
A Simple Recipe for Multilingual Grammatical Error Correction.
CoRR
Sascha Rothe, Jonathan Mallinson, Eric Malmi, Sebastian Krause, Aliaksei Severyn
2021 A* conf
Controlled Text Generation as Continuous Optimization with Multiple Constraints.
NeurIPS
Sachin Kumar, Eric Malmi, Aliaksei Severyn, Yulia Tsvetkov
2021 J jnl
Controlled Text Generation as Continuous Optimization with Multiple Constraints.
CoRR
Sachin Kumar, Eric Malmi, Aliaksei Severyn, Yulia Tsvetkov
2020 — conf
FELIX: Flexible Text Editing Through Tagging and Insertion.
EMNLP (Findings)
Jonathan Mallinson, Aliaksei Severyn, Eric Malmi, Guillermo Garrido
2020 J jnl
Felix: Flexible Text Editing Through Tagging and Insertion.
CoRR
Jonathan Mallinson, Aliaksei Severyn, Eric Malmi, Guillermo Garrido
2020 J jnl
Leveraging Pre-trained Checkpoints for Sequence Generation Tasks.
Trans. Assoc. Comput. Linguistics
Sascha Rothe, Shashi Narayan, Aliaksei Severyn
2020 — conf
Unsupervised Text Style Transfer with Padded Masked Language Models.
EMNLP (1)
Eric Malmi, Aliaksei Severyn, Sascha Rothe
2020 J jnl
Unsupervised Text Style Transfer with Padded Masked Language Models.
CoRR
Eric Malmi, Aliaksei Severyn, Sascha Rothe
2019 A* conf
Breaking the Softmax Bottleneck via Learnable Monotonic Pointwise Non-linearities.
ICML
Octavian Ganea, Sylvain Gelly, Gary Bécigneul, Aliaksei Severyn
2019 J jnl
Breaking the Softmax Bottleneck via Learnable Monotonic Pointwise Non-linearities.
CoRR
Octavian-Eugen Ganea, Sylvain Gelly, Gary Bécigneul, Aliaksei Severyn
2019 — conf
Encode, Tag, Realize: High-Precision Text Editing.
EMNLP/IJCNLP (1)
Eric Malmi, Sebastian Krause, Sascha Rothe, Daniil Mirylenka, Aliaksei Severyn
2019 J jnl
Encode, Tag, Realize: High-Precision Text Editing.
CoRR
Eric Malmi, Sebastian Krause, Sascha Rothe, Daniil Mirylenka, Aliaksei Severyn
2019 J jnl
Leveraging Pre-trained Checkpoints for Sequence Generation Tasks.
CoRR
Sascha Rothe, Shashi Narayan, Aliaksei Severyn
2019 — conf
Using Audio Transformations to Improve Comprehension in Voice Question Answering.
CLEF
Aleksandr Chuklin, Aliaksei Severyn, Johanne R. Trippas, Enrique Alfonseca, Hanna Silén, Damiano Spina
2018 J jnl
Adversarial Neural Networks for Cross-lingual Sequence Tagging.
CoRR
Heike Adel, Anton Bryl, David Weiss, Aliaksei Severyn
2018 J jnl
Eval all, trust a few, do wrong to none: Comparing sentence generation models.
CoRR
Ondrej Cífka, Aliaksei Severyn, Enrique Alfonseca, Katja Filippova
2018 J jnl
On Accurate Evaluation of GANs for Language Generation.
CoRR
Stanislau Semeniuta, Aliaksei Severyn, Sylvain Gelly
2018 J jnl
Prosody Modifications for Question-Answering in Voice-Only Settings.
CoRR
Aleksandr Chuklin, Aliaksei Severyn, Johanne R. Trippas, Enrique Alfonseca, Hanna Silén, Damiano Spina
2017 A* conf
A Hybrid Convolutional Variational Autoencoder for Text Generation.
EMNLP
Stanislau Semeniuta, Aliaksei Severyn, Erhardt Barth
2017 J jnl
A Hybrid Convolutional Variational Autoencoder for Text Generation.
CoRR
Stanislau Semeniuta, Aliaksei Severyn, Erhardt Barth
2017 J jnl
Avoiding Your Teacher's Mistakes: Training Neural Networks with Controlled Weak Supervision.
CoRR
Mostafa Dehghani, Aliaksei Severyn, Sascha Rothe, Jaap Kamps
2017 J jnl
Learning to Learn from Weak Supervision by Full Supervision.
CoRR
Mostafa Dehghani, Aliaksei Severyn, Sascha Rothe, Jaap Kamps
2017 A* conf
Leveraging Large Amounts of Weakly Supervised Data for Multi-Language Sentiment Classification.
WWW
Jan Deriu, Aurélien Lucchi, Valeria De Luca, Aliaksei Severyn, Simon Müller, Mark Cieliebak, Thomas Hofmann, Martin Jaggi
2017 J jnl
Leveraging Large Amounts of Weakly Supervised Data for Multi-Language Sentiment Classification.
CoRR
Jan Deriu, Aurélien Lucchi, Valeria De Luca, Aliaksei Severyn, Simon Müller, Mark Cieliebak, Thomas Hofmann, Martin Jaggi
2017 A* conf
Neural Ranking Models with Weak Supervision.
SIGIR
Mostafa Dehghani, Hamed Zamani, Aliaksei Severyn, Jaap Kamps, W. Bruce Croft
2017 J jnl
Neural Ranking Models with Weak Supervision.
CoRR
Mostafa Dehghani, Hamed Zamani, Aliaksei Severyn, Jaap Kamps, W. Bruce Croft
2017 — conf
RelTextRank: An Open Source Framework for Building Relational Syntactic-Semantic Text Pair Representations.
ACL (System Demonstrations)
Kateryna Tymoshenko, Alessandro Moschitti, Massimo Nicosia, Aliaksei Severyn
2016 — conf
Globally Normalized Transition-Based Neural Networks.
ACL (1)
Daniel Andor, Chris Alberti, David Weiss, Aliaksei Severyn, Alessandro Presta, Kuzman Ganchev, Slav Petrov, Michael Collins
2016 J jnl
Globally Normalized Transition-Based Neural Networks.
CoRR
Daniel Andor, Chris Alberti, David Weiss, Aliaksei Severyn, Alessandro Presta, Kuzman Ganchev, Slav Petrov, Michael Collins
2016 J jnl
Modeling Relational Information in Question-Answer Pairs with Convolutional Neural Networks.
CoRR
Aliaksei Severyn, Alessandro Moschitti
2016 J jnl
Multi-lingual opinion mining on YouTube.
Inf. Process. Manag.
Aliaksei Severyn, Alessandro Moschitti, Olga Uryupina, Barbara Plank, Katja Filippova
2016 B conf
Recurrent Dropout without Memory Loss.
COLING
Stanislau Semeniuta, Aliaksei Severyn, Erhardt Barth
2016 J jnl
Recurrent Dropout without Memory Loss.
CoRR
Stanislau Semeniuta, Aliaksei Severyn, Erhardt Barth
2015 — conf
Distributional Neural Networks for Automatic Resolution of Crossword Puzzles.
ACL (2)
Aliaksei Severyn, Massimo Nicosia, Gianni Barlacchi, Alessandro Moschitti
2015 A* conf
Learning to Rank Short Text Pairs with Convolutional Deep Neural Networks.
SIGIR
Aliaksei Severyn, Alessandro Moschitti
2015 — —
Modelling input texts: from Tree Kernels to Deep Learning.
Aliaksei Severyn
2015 — conf
On the Automatic Learning of Sentiment Lexicons.
HLT-NAACL
Aliaksei Severyn, Alessandro Moschitti
2015 A* conf
Twitter Sentiment Analysis with Deep Convolutional Neural Networks.
SIGIR
Aliaksei Severyn, Alessandro Moschitti
2015 — conf
UNITN: Training Deep Convolutional Neural Network for Twitter Sentiment Classification.
SemEval@NAACL-HLT
Aliaksei Severyn, Alessandro Moschitti
2014 A* conf
A syntax-aware re-ranker for microblog retrieval.
SIGIR
Aliaksei Severyn, Alessandro Moschitti, Manos Tsagkias, Richard Berendsen, Maarten de Rijke
2014 A conf
Encoding Semantic Resources in Syntactic Structures for Passage Reranking.
EACL
Kateryna Tymoshenko, Alessandro Moschitti, Aliaksei Severyn
2014 — conf
Opinion Mining on YouTube.
ACL (1)
Aliaksei Severyn, Alessandro Moschitti, Olga Uryupina, Barbara Plank, Katja Filippova
2014 B conf
SenTube: A Corpus for Sentiment Analysis on YouTube Social Media.
LREC
Olga Uryupina, Barbara Plank, Aliaksei Severyn, Agata Rotondi, Alessandro Moschitti
2013 A* conf
Automatic Feature Engineering for Answer Selection and Extraction.
EMNLP
Aliaksei Severyn, Alessandro Moschitti
2013 A conf
Building structures from classifiers for passage reranking.
CIKM
Aliaksei Severyn, Massimo Nicosia, Alessandro Moschitti
2013 A* conf
Fast Linearization of Tree Kernels over Large-Scale Data.
IJCAI
Aliaksei Severyn, Alessandro Moschitti
2013 B conf
Learning Adaptable Patterns for Passage Reranking.
CoNLL
Aliaksei Severyn, Massimo Nicosia, Alessandro Moschitti
2013 — conf
Learning Semantic Textual Similarity with Structural Representations.
ACL (2)
Aliaksei Severyn, Massimo Nicosia, Alessandro Moschitti
2013 — conf
iKernels-Core: Tree Kernel Learning for Textual Similarity.
*SEM@NAACL-HLT
Aliaksei Severyn, Massimo Nicosia, Alessandro Moschitti
2012 J jnl
Fast support vector machines for convolution tree kernels.
Data Min. Knowl. Discov.
Aliaksei Severyn, Alessandro Moschitti
2012 A* conf
Structural relationships for large-scale learning of answer re-ranking.
SIGIR
Aliaksei Severyn, Alessandro Moschitti
2011 — conf
Fast Support Vector Machines for Structural Kernels.
ECML/PKDD (3)
Aliaksei Severyn, Alessandro Moschitti
2011 — conf
Large-Scale Learning with Structural Kernels for Class-Imbalanced Datasets.
EternalS@FET
Aliaksei Severyn, Alessandro Moschitti
2010 — conf
Large-Scale Support Vector Learning with Structural Kernels.
ECML/PKDD (3)
Aliaksei Severyn, Alessandro Moschitti