Taisiya Glushkova

Hi! I'm a PhD student at SARDINE lab at Instituto Superior Técnico, supervised by André F. T. Martins and Chrysoula Zerva. Based in Lisbon, Portugal.


Email  /  CV  /  Google Scholar  /  Twitter  /  Github  /  LinkedIn

profile photo

About me

I am broadly interested in LLMs, Natural Language Generation Evaluation, Interpretability and Uncertainty Estimation. Currently, my research revolves around improving robustness of NLG evaluation models and developing methods that can quantify and communicate the uncertainty associated with the outputs of these models.

During my PhD I was working on uncertainty-aware MT evaluation, aiming to create more trustworthy systems which are robust to the variation observed across different languages and domains.

Before joining IST, I received a MSc and BSc in Computer Science at CS HSE in Moscow, Russia.

When not at my computer, I like to hike and paint with watercolor!

I will soon finish my PhD and be on the job market for industry research positions!


News
• June 2023: Our work is presented at EAMT in Tampere, Finland.
• Apr 2023: "BLEU Meets COMET: Combining Lexical and Neural Metrics Towards Robust Machine Translation Evaluation" got accepted to EAMT 2023!
• Dec 2022: Presenting a poster at EMNLP in Abu Dhabi, UAE.
• Nov 2022: Participating in a poster session at CMU Portugal 2022 Summit.
• Oct 2022: "Disentabgling Uncertainty in Machine Translation Evaluation" got accepted to EMNLP 2022!
• June 2022: Research Summer Internship at CMU within the scope of the MAIA project!
• Nov 2021: Presenting at EMNLP WMT21 workshop in Punta Cana, Dominican Republic.
• Aug 2021: "Uncertainty-Aware Machine Translation Evaluation" got accepted to EMNLP 2021!
• Sep 2020: Starting my PhD at IST under the scope of a collaborative project MAIA (Multilingual AI Agent Assistants).
• July 2019: Applied AI Research Summer Internship at Unbabel!

Selected Publications
BLEU Meets COMET: Combining Lexical and Neural Metrics Towards Robust Machine Translation Evaluation
Taisiya Glushkova, Chrysoula Zerva, André F. T. Martins
EAMT, Tampere, Finland; June 2023
[ ACL Anthology / poster ]

Disentangling Uncertainty in Machine Translation Evaluation
Chrysoula Zerva, Taisiya Glushkova, Ricardo Rei, André F. T. Martins
EMNLP, Abu Dhabi, UAE; December 2022
[ ACL Anthology / poster ]

COMET-22: Unbabel-IST 2022 Submission for the Metrics Shared Task
Ricardo Rei, José GC De Souza, Duarte Alves, Chrysoula Zerva, Ana C Farinha, Taisiya Glushkova, Alon Lavie, Luisa Coheur, André F. T. Martins
EMNLP WMT, Abu Dhabi, UAE; December 2022
[ ACL Anthology / poster ]

CometKiwi: IST-Unbabel 2022 Submission for the Quality Estimation Shared Task
Ricardo Rei, Marcos Treviso, Nuno M. Guerreiro, Chrysoula Zerva, Ana C Farinha, Christine Maroti, José GC De Souza, Taisiya Glushkova, Duarte Alves, Alon Lavie, Luisa Coheur, André F. T. Martins
EMNLP WMT, Abu Dhabi, UAE; December 2022
[ ACL Anthology ]

Uncertainty-Aware Machine Translation Evaluation
Taisiya Glushkova, Chrysoula Zerva, Ricardo Rei, André F. T. Martins
EMNLP Findings, Punta Cana, Dominican Republic; November 2021
[ ACL Anthology / slides ]

IST-Unbabel 2021 Submission for the Quality Estimation Shared Task
Chrysoula Zerva, Daan van Stigt, Ricardo Rei, Ana C Farinha, Pedro G. Ramos, José GC De Souza, Taisiya Glushkova, Miguel Vera, Fabio Kepler, André F. T. Martins
EMNLP WMT, Punta Cana, Dominican Republic; November 2021
[ WMT21 / poster ]

Are References Really Needed? Unbabel-IST 2021 Submission for the Metrics Shared Task
Ricardo Rei, Ana C Farinha, Chrysoula Zerva, Daan van Stigt, Craig Stewart, Pedro G. Ramos, Taisiya Glushkova, André F. T. Martins, Alon Lavie
EMNLP WMT, Punta Cana, Dominican Republic; November 2021
[ WMT21 / poster ]

Credits to Jon Barron for the template, thanks!