Recognition-Free Question Answering on Handwritten Document Collections

Tüselmann, Oliver; Müller, Friedrich; Wolf, Fabian; Fink, Gernot A.

doi:10.1007/978-3-031-21648-0_18

Cited by 4 publications

(1 citation statement)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…• Key Information Extraction (KIE) assigns each word a semantic entity label from predefined categories ( Šimsa et al 2023;Jaume, Ekenel, and Thiran 2019;Sun et al 2021;Park et al 2019;Huang et al 2019). • Single-page QA is a task of QA on single-page documents and focuses on document layout and textual content understanding (Tanaka, Nishida, and Yoshida 2021;Chen et al 2021;Mishra et al 2019;Mathew, Karatzas, and Jawahar 2021;Tüselmann et al 2022).…”

Section: Dataset Collectionmentioning

confidence: 99%

Event Report: NTT Communication Science Laboratories Open House 2022

Tanaka¹,

Sano²,

Wu³

et al. 2022

NTT Technical Review

View full text Add to dashboard Cite

The operator learning has received significant attention in recent years, with the aim of learning a mapping between function spaces. Prior works have proposed deep neural networks (DNNs) for learning such a mapping, enabling the learning of solution operators of partial differential equations (PDEs). However, these works still struggle to learn dynamics that obeys the laws of physics. This paper proposes Energy-consistent Neural Operators (ENOs), a general framework for learning solution operators of PDEs that follows the energy conservation or dissipation law from observed solution trajectories. We introduce a novel penalty function inspired by the energy-based theory of physics for training, in which the energy functional is modeled by another DNN, allowing one to bias the outputs of the DNN-based solution operators to ensure energetic consistency without explicit PDEs. Experiments on multiple physical systems show that ENO outperforms existing DNN models in predicting solutions from data, especially in super-resolution settings. KeywordsOperator learning • Energy-based theory • Hamiltonian mechanics • Partial differential equations * Citation: Authors. Title. Pages.... DOI:000000/11111.2 Note that PIML refers to the field of machine learning for exploiting various forms of physics knowledge and is distinct from PINNs that directly use PDEs, which is one approach in PIML.

show abstract