Calibration and Uncertainty for Structured Semantic Parsers Paper P2: Parser Calibration & Uncertainty; ALIGN100, 2/7

This paper develops theory, algorithms, and evaluation methodology for calibrating struc
tured outputs produced by syntactic and semantic parsers (UD, AMR, SDP). It extends scalar
calibration techniques (temperature scaling, Brier score) to transport-plan and graph-structured
predictions, proposes parametric and post-hoc calibration maps for structured plans, and provides
empirical protocols and diagnostics for measuring calibration in downstream extraction tasks.
The manuscript situates the contributions within recent advances in calibration and uncertainty
quantification for deep models and graph neural networks, and supplies pseudocode, theoretical
bounds linking structured calibration to downstream risk, and a reproducible experimental plan .