Search

Your search keyword '"Guo, Jialiang"' showing total 540 results
Start Over Author "Guo, Jialiang"
540 results on '"Guo, Jialiang"'

9. Everything Is All It Takes: A Multipronged Strategy for Zero-Shot Cross-Lingual Information Extraction

Author

Yarmohammadi, Mahsa, Wu, Shijie, Marone, Marc, Xu, Haoran, Ebner, Seth, Qin, Guanghui, Chen, Yunmo, Guo, Jialiang, Harman, Craig, Murray, Kenton, White, Aaron Steven, Dredze, Mark, and Van Durme, Benjamin

Subjects
Computer Science - Computation and Language
Abstract

Zero-shot cross-lingual information extraction (IE) describes the construction of an IE model for some target language, given existing annotations exclusively in some other language, typically English. While the advance of pretrained multilingual encoders suggests an easy optimism of "train on English, run on any language", we find through a thorough exploration and extension of techniques that a combination of approaches, both new and old, leads to better performance than any one cross-lingual strategy in particular. We explore techniques including data projection and self-training, and how different pretrained encoders impact them. We use English-to-Arabic IE as our initial example, demonstrating strong performance in this setting for event extraction, named entity recognition, part-of-speech tagging, and dependency parsing. We then apply data projection and self-training to three tasks across eight target languages. Because no single set of techniques performs the best across all tasks, we encourage practitioners to explore various configurations of the techniques described in this work when seeking to improve on zero-shot training., Comment: EMNLP 2021

Published
2021

29. Model compression for faster structural separation of macromolecules captured by Cellular Electron Cryo-Tomography

Author

Guo, Jialiang, Zhou, Bo, Zeng, Xiangrui, Freyberg, Zachary, and Xu, Min

Subjects
Quantitative Biology - Quantitative Methods, Computer Science - Computer Vision and Pattern Recognition, Statistics - Machine Learning
Abstract

Electron Cryo-Tomography (ECT) enables 3D visualization of macromolecule structure inside single cells. Macromolecule classification approaches based on convolutional neural networks (CNN) were developed to separate millions of macromolecules captured from ECT systematically. However, given the fast accumulation of ECT data, it will soon become necessary to use CNN models to efficiently and accurately separate substantially more macromolecules at the prediction stage, which requires additional computational costs. To speed up the prediction, we compress classification models into compact neural networks with little in accuracy for deployment. Specifically, we propose to perform model compression through knowledge distillation. Firstly, a complex teacher network is trained to generate soft labels with better classification feasibility followed by training of customized student networks with simple architectures using the soft label to compress model complexity. Our tests demonstrate that our compressed models significantly reduce the number of parameters and time cost while maintaining similar classification accuracy., Comment: 8 pages

Published
2018

30. Atypical Developmental Trajectories of Early Perception among School-Age Children with Attention Deficit Hyperactivity Disorder during a Visual Search Task

Author

Luo, Xiangsheng, Guo, Jialiang, Li, Dongwei, Liu, Lu, Chen, Yanbo, Zhu, Yu, Johnstone, Stuart J., Wang, Yufeng, Song, Yan, and Sun, Li

Abstract

Attention deficit hyperactivity disorder (ADHD) is a neurodevelopmental disorder characterized by cognitive deficits associated with attention. Prior studies have revealed the potential impact of ADHD on basic perception and cognitive ability in patients with ADHD. In this study, bilateral posterior P1 and N1 were measured in 122 Chinese children aged 7-12 years (64 with ADHD) to investigate the developmental characteristics of early perception during visual processing in school-age children with ADHD. For children with ADHD, a larger P1 activity with an atypical developmental pattern was evoked and observed for the visual search performance. These findings offer new insights into the mechanisms of cognitive developmental deficits and intervention techniques in children with ADHD.

Published
2021
Full Text
View/download PDF

34. Dynamic Analysis and Optimization of the Coupling System of Vibrating Flip-Flow Screen and Material Group.

Author

Gong, Sanpeng, Wang, Chenhao, Guo, Jialiang, Qiao, Ziqi, Zhao, Guofeng, Fan, Junkai, Xu, Ningning, and Wang, Xinwen

Subjects
DISCRETE element method, PERIODIC motion, SHALE shakers, FINITE element method, SHEARING force
Abstract

Vibrating flip-flow screens (VFFSs) provide an effective solution for deeply screening moist and fine-grained minerals, and an accurate dynamic model of VFFSs is critical for its dynamic analysis and optimization, thereby improving the vibration stability and symmetry of VFFSs. In this paper, uniaxial tension, uniaxial compression, plane tension, and shear stress relaxation experiments were conducted on screen panel samples to illustrate that the third-order Ogden model and the generalized Maxwell model can accurately describe the hyperelasticity and viscoelasticity of screen panels. Then, the coupling method of finite element and discrete element was adopted to establish the simulation model of the screen panel and material group coupling system, and the dynamics of the coupling system under different loading conditions were explored. Finally, the dynamic model of the coupling system of VFFSs mass, screen panel, and material group was proposed, and the non-dominated sorting genetic algorithm II was applied to optimize the system's dynamic response. The results reveal that the use of optimized shear springs can reduce the relative amplitude change rate of the main and floating screen frame by 44.30% while maintaining the periodic motion of the VFFSs under operation conditions, greatly enhancing the stability of the VFFSs system. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

36. Integrating Transcriptome and Chemical Analyses to Provide Insights into Biosynthesis of Terpenoids and Flavonoids in the Medicinal Industrial Crop Andrographis paniculate and Its Antiviral Medicinal Parts

Author

Yu, Kuo, primary, Liang, Pengjie, additional, Yu, Heshui, additional, Liu, Hui, additional, Guo, Jialiang, additional, Yan, Xiaohui, additional, Li, Zheng, additional, Li, Guoqiang, additional, Wang, Ying, additional, and Wang, Chunhua, additional

Published
2024
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results