Universal Multi-Span Text Annotation through Pairwise Classification
Received: 23 Oct 2026 Revised: 28 Oct 2026 Accepted: 30 Oct 2026
Published: 2026, vol. 30, issue 4, pp. 361–364
Abstract
We propose a two-level grid-tagging method for identifying text spans and grouping them into annotation elements. The method supports overlapping and nested spans. We provide an analysis of results obtained with four configurations comprising three different text representation models and a large language model. Performance is evaluated using metrics computed by annotation matching.
Keywords: two-level text annotation, pairwise classification.
BibTeX
@article{IS-Kukuzei-Sedelnikova-Tsybanov-Rink-Maysuradze2026,
author = {Kukuzei, Nikita Alexandrovich and Sedelnikova, Olga Yuryevna and Tsybanov, Ilya Antonovich and Rink, Olga Leonidovna and Maysuradze, Archil Iverievich},
title = {{Universal Multi-Span Text Annotation through Pairwise Classification}},
journal = {Intelligent Systems. Theory and Applications},
year = {2026},
volume = {30},
number = {4},
pages = {361--364},
}
AMSBIB
\Bibitem{IS-Kukuzei-Sedelnikova-Tsybanov-Rink-Maysuradze2026}
\by N.\,A.~Kukuzei, O.\,Y.~Sedelnikova, I.\,A.~Tsybanov, O.\,L.~Rink, A.\,I.~Maysuradze
\paper Universal Multi-Span Text Annotation through Pairwise Classification
\jour Intelligent Systems. Theory and Applications
\yr 2026
\vol 30
\issue 4
\pages 361--364
\lang In Russian
Published under
Creative Commons Attribution 4.0 International (CC BY 4.0)
RU