@inproceedings{tukhtina-etal-2022-hse,
    title = "{HSE} at {T}empo{W}i{C}: Detecting Meaning Shift in Social Media with Diachronic Language Models",
    author = "Tukhtina, Elizaveta  and
      Kashleva, Kseniia  and
      Vydrina, Svetlana",
    editor = "Barbieri, Francesco  and
      Camacho-Collados, Jose  and
      Dhingra, Bhuwan  and
      Espinosa-Anke, Luis  and
      Gribovskaya, Elena  and
      Lazaridou, Angeliki  and
      Loureiro, Daniel  and
      Neves, Leonardo",
    booktitle = "Proceedings of the First Workshop on Ever Evolving NLP (EvoNLP)",
    month = dec,
    year = "2022",
    address = "Abu Dhabi, United Arab Emirates (Hybrid)",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/2022.evonlp-1.6/",
    doi = "10.18653/v1/2022.evonlp-1.6",
    pages = "35--38",
    abstract = "This paper describes our methods for temporal meaning shift detection, implemented during the TempoWiC shared task. We present two systems: with and without time span data usage. Our approaches are based on the language models fine-tuned for Twitter domain. Both systems outperformed all the competition`s baselines except TimeLMs-SIM. Our best submission achieved the macro-F1 score of 70.09{\%} and took the 7th place. This result was achieved by using diachronic language models from the TimeLMs project."
}