My Profile

Tsvetomila Mihaylova

Instituto de Telecomunicações, Lisbon, Portugal

I am a PhD student in the DeepSPIN project at Instituto de Telecomunicações in Lisbon, Portugal, supervised by André Martins and Vlad Niculae. My work is on Machine Learning and Natural Language Processing, with my current research focused on models with latent structures.

Research Interests

  • Natural Language Processing
  • Machine Learning

News

  • Our work on Scheduled Sampling for Transformers was accepted at the Student Research Workshop at ACL 2019. May 2019
  • Our tutorial on Latent Structure Models for NLP has been accepted to be presented at ACL 2019! February 2019
  • I started a PhD in the DeepSPIN project at Instituto de Telecomunicações in Lisbon, Portugal, supervised by André Martins and Vlad Niculae. June 2018
  • I am part of the organizers of the SemEval 2019 Task 8 on Fact Checking in Community Question Answering Forums. May 2018
  • Our paper "Fact Checking in Community Forums" was accepted at AAAI-18. November 2017
  • I presented our paper "Do Not Trust the Trolls: Predicting Credibility in Community Question Answering Forums" at the RANLP 2017 conference in Varna, Bulgaria. September 2017
  • I defended my master thesis "Fact-Checking in Community Question Answering". July 2017
  • I presented our paper "Finding Good Answers in Online Forums: Community Question Answering for Bulgarian" at the CLIB 2016 conference in Sofia, Bulgaria. September 2016
  • Our system for PAN 2016 Author Obfuscation Task ranked 1st in terms of safety. May 2016
  • Our system for SemEval Task 3 on Community Question Answering ranked 1st in the main Subtask C. February 2016

Publications

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