Inference Cost Estimation for Selecting a Structural Text Annotation Model
Received: 23 Oct 2026 Revised: 03 Nov 2026 Accepted: 05 Nov 2026
Published: 2026, vol. 30, issue 4, pp. 405–408
Abstract
Model selection for practical deployment is governed by the trade-off between functional accuracy and cost of use. A cost-of-use estimation procedure is tailored to models for structurally complex text annotation. The aggregate estimate accounts for the full automatic annotation pipeline and returns the cost of annotating 1,000 texts. Models of differing architecture and size were compared across 21 datasets.
Keywords: structured text annotation; span detection and linking; nested spans; inference costs; model selection; operational costs.
BibTeX
@article{IS-Sedelnikova-Kukuzei-Tsybanov-Rink-Maysuradze-Ischenko2026,
author = {Sedelnikova, Olga Iuryevna and Kukuzei, Nikita Alexandrovich and Tsybanov, Ilya Antonovich and Rink, Olga Leonidovna and Maysuradze, Archil Iverievich and Ischenko, Roman Valeryevich},
title = {{Inference Cost Estimation for Selecting a Structural Text Annotation Model}},
journal = {Intelligent Systems. Theory and Applications},
year = {2026},
volume = {30},
number = {4},
pages = {405--408},
}
AMSBIB
\Bibitem{IS-Sedelnikova-Kukuzei-Tsybanov-Rink-Maysuradze-Ischenko2026}
\by O.\,I.~Sedelnikova, N.\,A.~Kukuzei, I.\,A.~Tsybanov, O.\,L.~Rink, A.\,I.~Maysuradze, R.\,V.~Ischenko
\paper Inference Cost Estimation for Selecting a Structural Text Annotation Model
\jour Intelligent Systems. Theory and Applications
\yr 2026
\vol 30
\issue 4
\pages 405--408
\lang In Russian
RU