Empirical Study of Transformers for Source Code N Chirkova, S Troshin ESEC/FSE 2021: ACM Joint European Software Engineering Conference and …, 2020 | 67 | 2020 |
On Power Laws in Deep Ensembles E Lobacheva, N Chirkova, M Kodryan, D Vetrov NeurIPS 2020: Advances in Neural Information Processing Systems, 2020 …, 2020 | 47 | 2020 |
Probing pretrained models of source code S Troshin, N Chirkova BlackboxNLP Workshop as EMNLP 2022, 2022 | 40 | 2022 |
Additive regularization for hierarchical multimodal topic modeling NA Chirkova, KV Vorontsov Journal Machine Learning and Data Analysis 2 (2), 187-200, 2016 | 37 | 2016 |
On the Periodic Behavior of Neural Network Training with Batch Normalization and Weight Decay E Lobacheva, M Kodryan, N Chirkova, A Malinin, DP Vetrov NeurIPS 2021: Advances in Neural Information Processing Systems 34, 2021 | 27 | 2021 |
Bayesian sparsification of recurrent neural networks E Lobacheva, N Chirkova, D Vetrov ICML Workshop on Learning to Generate Natural Language, 2017 | 19 | 2017 |
Bayesian compression for natural language processing N Chirkova, E Lobacheva, D Vetrov EMNLP 2018: 2018 Conference on Empirical Methods in Natural Language Processing, 2018 | 16 | 2018 |
Parameter-Efficient Finetuning of Transformers for Source Code S Ayupov, N Chirkova Workshop on Efficient Natural Language Processing at NeurIPS 2022, 2022 | 13 | 2022 |
A Simple Approach for Handling Out-of-Vocabulary Identifiers in Deep Learning for Source Code N Chirkova, S Troshin NAACL 2021: Annual Conference of the North American Chapter of the …, 2020 | 12 | 2020 |
Deep ensembles on a fixed memory budget: One wide network or several thinner ones? N Chirkova, E Lobacheva, D Vetrov arXiv preprint arXiv:2005.07292, 2020 | 9 | 2020 |
Structured Sparsification of Gated Recurrent Neural Networks E Lobacheva, N Chirkova, A Markovich, D Vetrov NeurIPS Workshop on Context and Compositionality in Biological and …, 2019 | 8 | 2019 |
Should you marginalize over possible tokenizations? N Chirkova, G Kruszewski, J Rozen, M Dymetman ACL 2023: 61st Annual Meeting of the Association for Computational Linguistics, 2023 | 7 | 2023 |
On the Embeddings of Variables in Recurrent Neural Networks for Source Code N Chirkova NAACL 2021: 2021 Conference of the North American Chapter of the Association …, 2021 | 6 | 2021 |
CodeBPE: Investigating Subtokenization Options for Large Language Model Pretraining on Source Code N Chirkova, S Troshin ICLR 2023, 2023 | 5 | 2023 |
Bayesian Sparsification of Gated Recurrent Neural Networks E Lobacheva, N Chirkova, D Vetrov NeurIPS Workshop on Compact Deep Neural Network Representation with …, 2018 | 4 | 2018 |
Zero-shot cross-lingual transfer in instruction tuning of large language models N Chirkova, V Nikoulina INLG 2024: 17th International Natural Language Generation Conference, 2024 | 3 | 2024 |
Key ingredients for effective zero-shot cross-lingual knowledge transfer in generative tasks N Chirkova, V Nikoulina NAACL 2024, 2024 | 3 | 2024 |
Retrieval-augmented generation in multilingual settings N Chirkova, D Rau, H Déjean, T Formal, S Clinchant, V Nikoulina ACL 2024 Workshop: Towards Knowledgeable Language Models, 2024 | 2 | 2024 |
On the Memorization Properties of Contrastive Learning I Sadrtdinov, N Chirkova, E Lobacheva ICML Workshop on Overparameterization: Pitfalls & Opportunities, 2021, 2021 | 2 | 2021 |
BERGEN: A Benchmarking Library for Retrieval-Augmented Generation D Rau, H Déjean, N Chirkova, T Formal, S Wang, V Nikoulina, ... Findings of EMNLP 2024, 2024 | 1 | 2024 |