SCOPE-Fact: Linguistic Scope-Guided Composition of Anchored Stochastic Operators for Predicting Event Factuality in Natural Language
- 1College of Intelligence Science and Engineering, Northeast Agricultural University, Harbin 150040, China
- 2Artificial Intelligence Research Institute, Northeast Forestry University, Harbin 150040, China
- 3School of Mechanical Engineering and Automation, Northeastern University, Shenyang 110819, China
Abstract
Event factuality prediction, a task in natural language processing, estimates the commitment conveyed by a text toward an event. Nested negation and modality require inference sensitive to the linguistic scope, but endpoint labels can leave intermediate transformations underdetermined. We introduce SCOPE-Fact, which learns five-state stochastic operators from isolated lexical and grammatical signatures and composes them in scope order. Parent–child commitment judgments constrain local transformations, while a log-determinant acquisition criterion allocates a fixed annotation budget. Unsupported inputs use an independent text classifier shared across mechanistic comparisons. Our analysis establishes conditional recovery and perturbation bounds, gives a necessary total-variation diagnostic for local representation adequacy, and characterizes observable order effects through commutators. With five ratings per proposition, the simultaneous adequacy bound is inconclusive at the population level. The reported empirical scores are 51.5% macro-F1 on MAVEN-FACT public development and 69.0%, 59.0%, and 48.0% pair accuracy under combination, order, and depth holdouts. Relative to an equally supervised nonlinear recurrence, the point differences are 51.5-51.0, 69.0-65.0, 59.0-55.0, and 48.0-43.0 percentage points. The combination-holdout difference from the no-anchor ablation is 69.0-58.0 points. These descriptive comparisons are interpreted jointly with routing coverage and paired uncertainty. The framework makes the predictive reuse of local commitment transformations testable within a defined linguistic core, while the mathematical analysis separates prediction from population identifiability and representation adequacy.
Related
- Weighted composition operators on the Fock space
- On the dynamics of composition operators: supercyclicity, odometers and translations
- Convexity of the Berezin range of composition operators induced by automorphisms of the Unit Ball in ℂn
- Weighted composition--differentiation operators on mixed-norm, derivative Hardy and F(p,q,s) spaces
- Schatten class membership of products of composition operators and their adjoints
BibTeX
@article{zhao2026scopefact,
title = {{SCOPE-Fact: Linguistic Scope-Guided Composition of Anchored Stochastic Operators for Predicting Event Factuality in Natural Language}},
author = {Yuting Zhao and Haochen Qi and Jun Long and Kaiyu Su and Jing Zhao and Xiangwei Kong and Qihao Xu},
journal = {Mathematics},
year = {2026},
month = nov,
doi = {10.3390/math14214016},
url = {https://www.mdpi.com/2227-7390/14/21/4016},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - SCOPE-Fact: Linguistic Scope-Guided Composition of Anchored Stochastic Operators for Predicting Event Factuality in Natural Language
AU - Yuting Zhao
AU - Haochen Qi
AU - Jun Long
AU - Kaiyu Su
AU - Jing Zhao
AU - Xiangwei Kong
AU - Qihao Xu
PY - 2026
DA - 2026/11/03
JO - Mathematics
DO - 10.3390/math14214016
UR - https://www.mdpi.com/2227-7390/14/21/4016
AB - Event factuality prediction, a task in natural language processing, estimates the commitment conveyed by a text toward an event. Nested negation and modality require inference sensitive to the linguistic scope, but endpoint labels can leave intermediate transformations underdetermined. We introduce SCOPE-Fact, which learns five-state stochastic operators from isolated lexical and grammatical signatures and composes them in scope order. Parent–child commitment judgments constrain local transformations, while a log-determinant acquisition criterion allocates a fixed annotation budget. Unsupported inputs use an independent text classifier shared across mechanistic comparisons. Our analysis establishes conditional recovery and perturbation bounds, gives a necessary total-variation diagnostic for local representation adequacy, and characterizes observable order effects through commutators. With five ratings per proposition, the simultaneous adequacy bound is inconclusive at the population level. The reported empirical scores are 51.5% macro-F1 on MAVEN-FACT public development and 69.0%, 59.0%, and 48.0% pair accuracy under combination, order, and depth holdouts. Relative to an equally supervised nonlinear recurrence, the point differences are 51.5-51.0, 69.0-65.0, 59.0-55.0, and 48.0-43.0 percentage points. The combination-holdout difference from the no-anchor ablation is 69.0-58.0 points. These descriptive comparisons are interpreted jointly with routing coverage and paired uncertainty. The framework makes the predictive reuse of local commitment transformations testable within a defined linguistic core, while the mathematical analysis separates prediction from population identifiability and representation adequacy.
SN - 2227-7390
ER -