Claims Browser

Morpheme+XPOS representation provides stronger parsing results than Eojeol-based representations, even when predictions are projected to the eojeol terminal domain

"Morpheme+XPOS gives the strongest results even after its predictions are projected to the eojeol terminal domain"

Fine-grained morphological and XPOS representations provide valuable evidence for constituency parsers under gold-annotation conditions

"Under these gold-annotation conditions, the results show that fine-grained morphological and XPOS representations provide valuable evidence for the evaluated parsers"

Eojeol+UPOS parsing substantially underperforms morphologically richer conditions despite eojeol terminals yielding shorter transition sequences

"Eojeol terminals yield shorter transition sequences, but Eojeol+UPOS parsing substantially underperforms the morphologically richer conditions"

Eojeol is a stable and interpretable surface domain for phrase-structure annotation when morpheme-level and XPOS information is retained as aligned morphosyntactic evidence

"linguistic and resource-design considerations motivate eojeol as a stable and interpretable surface domain for phrase-structure annotation, with morpheme-level and XPOS information retained as aligned morphosyntactic evidence"

Decentralized multitask learning can estimate task relationship graphs directly from distributed data without assuming known structure

"This paper investigates decentralized multitask learning over networks when the underlying task relationships are unknown. While existing graph-regularized multitask frameworks typically assume a known structure, practical settings often require learning inter-task dependencies directly from distributed data."

A two-phase decentralized strategy using Gaussian Markov random field priors can estimate graph Laplacians from noisy stochastic gradient iterates and enable cooperative multitask learning

"We propose a decentralized two-phase strategy that first estimates a generalized graph Laplacian from noisy non-cooperative stochastic gradient iterates, and subsequently exploits the learned graph to enable cooperative multitask diffusion learning. This framework is motivated by a Gaussian Markov random field prior, which gives rise to a decentralized maximum likelihood estimator for the graph Laplacian."

Cooperation enabled by learned task graphs significantly improves performance over non-cooperative learning and approaches true-graph baseline performance with sufficiently small estimation stepsizes

"Simulation results corroborate the theoretical findings and demonstrate that cooperation enabled by the learned task graph significantly improves performance over non-cooperative learning, while approaching the true-graph baseline when the estimation stepsize is sufficiently small."

Many commonly used retrieval and classification approaches return either pairwise similarity scores or class labels, but fewer methods provide concept-level scores that are directly traceable to terminological evidence

"Many commonly used retrieval and classification approaches return either pairwise similarity scores or one or more class labels, whereas fewer methods provide concept-level scores that are directly traceable to the terminological evidence supporting them."

ITL methodology can estimate affinity between textual units and structured reference concepts in a domain-agnostic and language-portable way

"We present \emph{Intelligent Target Locator} (ITL), a domain-agnostic and language-portable methodology that estimates the affinity between the textual units of a target document and the concepts defined in a \emph{Structured Reference Document} ($SRD$)."

ITL achieved perfect alignment in SDG evaluation, with every official goal statement reaching highest affinity with its corresponding concept

"We conduct an internal consistency assessment using the 17 Sustainable Development Goals (SDGs), evaluating each official goal statement against the $SRD$ induced from the same set of descriptors. Every statement reached its highest affinity with the corresponding concept, and the mean affinity across the remaining concepts stayed marginal relative to the mean reference affinity."

ITL offers a general basis for quantifying document alignment with structured frameworks while maintaining traceability to terminological evidence

"ITL thus offers a general basis for quantifying document alignment with structured frameworks while keeping each result traceable to the terminological evidence that supports it."

Traditional credit risk assessment methods fail to differentiate between temporal patterns indicative of credit risk and those reflecting general customer behavior, leading to suboptimal risk predictions

"Specifically, they fail to differentiate between temporal patterns indicative of credit risk and those reflecting general customer behavior or preferences, leading to suboptimal risk predictions."

The DTD-VAE framework achieves performance gains of 3.2%-4.86% in ROC-AUC and 6.41%-9.71% in Accuracy Ratio compared to existing methods on real-world datasets

"Extensive experiments on six real-world datasets demonstrate that the proposed framework consistently outperforms existing methods, achieving performance gains of 3.2%-4.86% in ROC-AUC and 6.41%-9.71% in Accuracy Ratio."

Existing point-cloud reconstruction pipelines typically return a single best-fit structure without uncertainty quantification

"existing point-cloud reconstruction pipelines typically return a single best-fit structure without uncertainty quantification"

A fully Bayesian framework for point-cloud data can accurately reconstruct closed curves with quantified uncertainty

"Numerical experiments, including synthetic examples and real-world LiDAR datasets, show accurate reconstructions and quantified uncertainty over the recovered curves"

Learning cannot be reduced to proper learning by enlarging the hypothesis class, as there exists a learnable multiclass problem that cannot be embedded in any properly learnable class

"we exhibit a learnable multiclass problem that cannot be embedded in any properly learnable class, meaning learning cannot be reduced to proper learning by enlarging the hypothesis class"

Proper learning can require training error, and every properly learnable class admits a proper learner making o(m) errors on samples of size m, but every prescribed sublinear scale is necessary for some properly learnable problem

"proper learning can require training error and characterize this phenomenon precisely: every properly learnable class admits a proper learner making $o(m)$ errors on samples of size $m$, but every prescribed sublinear scale $a_m=o(m)$ is necessary for some properly learnable problem"

Regularization is not a general learner, as there exists a properly learnable class that cannot be learned by any Structural Risk Minimization learner, and a learnable class that cannot be learned by any local regularizer

"regularization is not a general learner: we exhibit a properly learnable class that cannot be learned by any Structural Risk Minimization (SRM) learner, and a learnable class that cannot be learned by any local regularizer"