Asosiy kontentga oʻtish
Preprint

Morphology-Aware Span-First Structured ABSA for Uzbek: Boundary Modeling and a Protocol for Cross-Lingual Turkic Transfer

Elov Botir BoltayevichAlisher Navo'i Tashkent State University of Uzbek Language and LiteratureRuhillo Alaev²Alisher Navo'i Tashkent State University of Uzbek Language and LiteratureSulton NormamatovAlisher Navo'i Tashkent State University of Uzbek Language and LiteratureAlisher Abdullayev³Ministry of Higher Education, Science and Innovation of the Republic of UzbekistanElov JamshidTashkent University of Information TechnologyMuhayyo Karimovna XAKIMOVAAlisher Navo'i Tashkent State University of Uzbek Language and LiteratureMurotali LatipovGulistan State University
2026en
ABI

Annotatsiya

Abstract Recovering aspect mentions is insufficient for structured sentiment analysis when their opinions, occurrences, or attributes are wrong. We study these errors in Uzbek educational texts using UzEDU-ABSA: 7,440 records, 5,683 texts, and 5,622 allocation groups. MorphoSpan-Uz augments XLM-R with a token-level byte convolution, eight transparent suffix features, and auxiliary endpoint supervision with span–endpoint consistency. It maps contiguous word spans to original Unicode offsets and predicts six-field tuples. We reassess eight archived systems across five seeds and independently reproduce their saved final-test metrics. On 744 records from 567 texts and 564 groups, mean candidate aspect exact F1 is 73.11 ± 14.12 and strict tuple F1 is 26.15 ± 8.16, versus 65.61 ± 18.79 and 19.09 ± 7.44 for XLM-R span. Scores are percentages and dispersions are sample standard deviations across seeds. Retrospective paired hierarchical bootstrap intervals for the improvements are [2.14, 14.49] and [4.35, 9.93] percentage points. Byte features and boundary supervision improve observed means; morphology gains are smaller and metric-dependent. Target-only low-rank adaptation (LoRA) produces no candidates, and constrained generators remain syntactically valid despite low tuple accuracy. Offset annotations have mixed review provenance: 525 records have documented human span confirmation. Conclusions are therefore conditional on annotation quality; prediction-level reproducibility does not establish checkpoint reproducibility. Turkish-to-Uzbek transfer is specified as a prospective protocol; no cross-lingual gain is claimed from the completed experiments.

Hali tarjima qilinmagan

Identifikatorlar

Iqtiboslar va manbalar