Irina Nikishina

I am a postdoc at Language Technology Group, Universität Hamburg hosted by Chris Biemann.

I have got my PhD in Computer Science at Skolkovo Institute of Science and Technology in 2022. I worked on the Taxonomy Enrichment task under the supervision of Alexander Panchenko.

My research interests include Taxonomies, Retrieval Augmented Generation, Question Answering, and NLP in application to Linguistics. Currently, I am interested in NLP for Low-Resource Languages.

Google Scholar

news

Oct 6, 2024	Our paper “Low-Resource Machine Translation through the Lens of Personalized Federated Learning” has been accepted to EMNLP 2024 findings! 🎉
Jun 16, 2024	Have a look on our preprint on MT for Lower-Resource languages: arxiv! It was a fruitful collaboration with ML lab in MBZUAI
Jun 1, 2024	Our paper about TaxoLLaMA has been accepted to ACL 2024 (main)! 🎉🎉🎉

selected publications

TaxoLLaMA: WordNet-based Model for Solving Multiple Lexical Semantic Tasks

Viktor Moskvoretskii, Ekaterina Neminova, Alina Lobanova, and 2 more authors

In Proceedings of the 62nd Conference of the Association for Computational Linguistics, Aug 2024

Bib

@inproceedings{moskvoretskii-etal-2024-taxollama,
  title = {TaxoLLaMA: WordNet-based Model for Solving Multiple Lexical Semantic Tasks},
  author = {Moskvoretskii, Viktor and Neminova, Ekaterina and Lobanova, Alina and Panchenko, Alexander and Nikishina, Irina},
  booktitle = {Proceedings of the 62nd Conference of the Association for Computational Linguistics},
  month = aug,
  year = {2024},
  address = {Bangkok, Tailand},
  publisher = {Association for Computational Linguistics},
  dimensions = {false},
}

Low-Resource Machine Translation through the Lens of Personalized Federated Learning

Viktor Moskvoretskii, Nazarii Tupitsa, Chris Biemann, and 3 more authors

In Proceedings of the The 2024 Conference on Empirical Methods in Natural Language Processing, Nov 2024

Abs Bib

We present a new approach based on the Personalized Federated Learning algorithm MeritFed that can be applied to Natural Language Tasks with heterogeneous data. We evaluate it on the Low-Resource Machine Translation task, using the dataset from the Large-Scale Multilingual Machine Translation Shared Task (Small Track #2) and the subset of Sami languages from the multilingual benchmark for Finno-Ugric languages. In addition to its effectiveness, MeritFed is also highly interpretable, as it can be applied to track the impact of each language used for training. Our analysis reveals that target dataset size affects weight distribution across auxiliary languages, that unrelated languages do not interfere with the training, and auxiliary optimizer parameters have minimal impact. Our approach is easy to apply with a few lines of code, and we provide scripts for reproducing the experiments at thishttps://github.com/VityaVitalich/MeritFed
@inproceedings{moskvoretskii2024low, title = {Low-Resource Machine Translation through the Lens of Personalized Federated Learning}, author = {Moskvoretskii, Viktor and Tupitsa, Nazarii and Biemann, Chris and Horvath, Samuel and Gorbunov, Eduard and Nikishina, Irina}, journal = {arXiv preprint arXiv:2406.12564}, booktitle = {Proceedings of the The 2024 Conference on Empirical Methods in Natural Language Processing}, month = nov, year = {2024}, address = {Miami, USA}, publisher = {Association for Computational Linguistics}, dimensions = {false}, }
Studying Taxonomy Enrichment on Diachronic WordNet Versions

Irina Nikishina, Varvara Logacheva, Alexander Panchenko, and 1 more author

In Proceedings of the 28th International Conference on Computational Linguistics, Dec 2020

Abs Bib

Ontologies, taxonomies, and thesauri have always been in high demand in a large number of NLP tasks. However, most studies are focused on the creation of lexical resources rather than the maintenance of the existing ones and keeping them up-to-date. In this paper, we address the problem of taxonomy enrichment. Namely, we explore the possibilities of taxonomy extension in a resource-poor setting and present several methods which are applicable to a large number of languages. We also create novel English and Russian datasets for training and evaluating taxonomy enrichment systems and describe a technique of creating such datasets for other languages.
@inproceedings{nikishina-etal-2020-studying, title = {Studying Taxonomy Enrichment on Diachronic {W}ord{N}et Versions}, author = {Nikishina, Irina and Logacheva, Varvara and Panchenko, Alexander and Loukachevitch, Natalia}, editor = {Scott, Donia and Bel, Nuria and Zong, Chengqing}, booktitle = {Proceedings of the 28th International Conference on Computational Linguistics}, month = dec, year = {2020}, address = {Barcelona, Spain (Online)}, publisher = {International Committee on Computational Linguistics}, url = {https://aclanthology.org/2020.coling-main.276}, pages = {3095--3106}, }