Tsvetomila Mihaylova - Academic Resume

I am postdoctoral researcher at Aalto University, in the Intelligent Robotics group lead by Ville Kyrki.
I did my PhD in the DeepSPIN project at Instituto de Telecomunicações in Lisbon, Portugal, supervised by André Martins and Vlad Niculae. My PhD work was on machine learning and natural language processing, with a focus on modeling the structure of language with deep neural networks.

Research Interests

Machine Learning
Robotics
Natural Language Processing

Recent Personal News

We are organizing a workshop SAFE-DRIVE: Data-Driven Simulations and Multi-Agent Interactions for Autonomous Vehicle Safety, which will take place as part of IEEE IV 2024. Paper submission deadline: 1st February 2024.
I started a new position as a Postdoctoral Researcher at Aalto University. March 2023
A preprint of the book Discrete Latent Structure in Neural Networks, based on our tutorial Latent Structure Models for Natural Language Processing is available on arXiv. January 2023
I took part in the Ocado Robotics Accelerator. October 2022
I successfully defended my PhD thesis "Modeling Structure with Deep Neural Networks for Natural Language Processing". July 2022
Our paper Modeling Structure with Undirected Neural Networks was accepted to ICML 2022. May 2022

Publications

2023

Vlad Niculae, Caio F. Corro, Nikita Nangia, Tsvetomila Mihaylova, André F. T. Martins (2023):
Discrete Latent Structure in Neural Networks,
preprint

2022

Tsvetomila Mihaylova, Vlad Niculae, André F.T. Martins (2022):
Modeling Structure with Undirected Neural Networks,
The 39th International Conference on Machine Learning (ICML 2022)

2021

Tsvetomila Mihaylova, Souhila Djabri, Dinara Gimadi, Ivelina Nikolova-Koleva (2021):
Proceedings of the Student Research Workshop Associated with RANLP 2021,
Recent Advances in Natural Language Processing (RANLP 2021)

2020

Tsvetomila Mihaylova, Vlad Niculae, André F.T. Martins (2020):
Understanding the Mechanics of SPIGOT: Surrogate Gradients for Latent Structure Learning,
The 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP 2020)

2019

Tsvetomila Mihaylova, André F.T. Martins (2019):
Scheduled Sampling for Transformers,
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop, (ACL 2019 SRW)
André FT Martins, Tsvetomila Mihaylova, Nikita Nangia, Vlad Niculae (2019):
Latent Structure Models for Natural Language Processing,
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics: Tutorial Abstracts (ACL 2019 Tutorial)
Pepa Atanasova, Preslav Nakov, Lluís Màrquez, Alberto Barrón-Cedeño, Georgi Karadzhov, Tsvetomila Mihaylova, Mitra Mohtarami, James Glass (2019):
Automatic fact-checking using context and discourse information,
Journal of Data and Information Quality (JDIQ 2019)
Tsvetomila Mihaylova, Georgi Karadjov, Pepa Atanasova, Ramy Baly, Mitra Mohtarami, Preslav Nakov (2019):
SemEval-2019 task 8: Fact checking in community question answering forums,
Proceedings of the 13th International Workshop on Semantic Evaluation (SemEval 2019)

2018

Tsvetomila Mihaylova, Preslav Nakov, Lluıs Marquez, Alberto Barron-Cedeno, Mitra Mohtarami, Georgi Karadzhov, James Glass (2018):
Fact Checking in Community Forums
The Thirty-Second AAAI Conference on Artificial Intelligence (AAAI-18)

2017

Preslav Nakov, Tsvetomila Mihaylova, Lluís Màrquez, Yashkumar Shiroya, Ivan Koychev (2017):
Do Not Trust the Trolls: Predicting Credibility in Community Question Answering Forums
RANLP-2017
Tsvetomila Mihaylova (2017):
Fact-Checking in Community Question Answering
Master Thesis
Georgi Karadzhov, Tsvetomila Mihaylova, Yasen Kiprov, Georgi Georgiev, Ivan Koychev, Preslav Nakov (2017):
The Case for Being Average: A Mediocrity Approach to Style Masking and Author Obfuscation
International Conference of the Cross-Language Evaluation Forum for European Languages, Springer, pages 173-185

2016

Tsvetomila Mihaylova, Ivan Koychev, Preslav Nakov, Ivelina Nikolova (2016):
Finding Good Answers in Online Forums: Community Question Answering for Bulgarian
Second International Conference Computational Linguistics in Bulgaria (CLIB 2016)
Tsvetomila Mihaylova, Georgi Karadjov, Preslav Nakov, Yasen Kiprov, Georgi Georgiev, Ivan Koychev (2016):
SU@ PAN’2016: Author Obfuscation - Notebook for PAN at CLEF 2016
Conference and Labs of the Evaluation Forum, CLEF 2016
Tsvetomila Mihaylova, Pepa Gencheva, Martin Boyanov, Ivana Yovcheva, Todor Mihaylov, Momchil Hardalov, Yasen Kiprov, Daniel Balchev, Ivan Koychev, Preslav Nakov, Ivelina Nikolova, Galia Angelova (2016):
SUper Team at SemEval-2016 Task 3: Building a Feature-Rich System for Community Question Answering
SemEval@ NAACL-HLT 2016