SubmissionNumber#=%=#276
FinalPaperTitle#=%=#DeepPavlov at SemEval-2024 Task 8: Leveraging Transfer Learning for Detecting Boundaries of Machine-Generated Texts
ShortPaperTitle#=%=#
NumberOfPages#=%=#9
CopyrightSigned#=%=#Anastasia Voznyuk
JobTitle#==#Researcher
Organization#==#MIPT
Abstract#==#The Multigenerator, Multidomain, and Multilingual Black-Box Machine-Generated Text Detection shared task in the SemEval-2024 competition aims to tackle the problem of misusing collaborative human-AI writing. Although there are a lot of existing detectors of AI content, they are often designed to give a binary answer and thus may not be suitable for more nuanced problem of finding the boundaries between human-written and machine-generated texts, while hybrid human-AI writing becomes more and more popular. In this paper, we address the boundary detection problem. Particularly, we present a pipeline for augmenting data for supervised fine-tuning of DeBERTaV3. We receive new best MAE score, according to the leaderboard of the competition, with this pipeline.
Author{1}{Firstname}#=%=#Anastasia
Author{1}{Lastname}#=%=#Voznyuk
Author{1}{Username}#=%=#tropaeolum
Author{1}{Email}#=%=#vozniuk.ae@phystech.edu
Author{1}{Affiliation}#=%=#Moscow Institute of Physics and Technology
Author{2}{Firstname}#=%=#Vasily
Author{2}{Lastname}#=%=#Konovalov
Author{2}{Username}#=%=#vaskonov
Author{2}{Email}#=%=#vaskoncv@gmail.com
Author{2}{Affiliation}#=%=#MIPT

==========
èéáğö