Search Results for author: Cong Chen

Found 14 papers, 1 papers with code

“细粒度英汉机器翻译错误分析语料库”的构建与思考(Construction of Fine-Grained Error Analysis Corpus of English-Chinese Machine Translation and Its Implications)

no code implementations CCL 2020 Bailian Qiu, Mingwen Wang, Maoxi Li, Cong Chen, Fan Xu

机器翻译错误分析旨在找出机器译文中存在的错误, 包括错误类型、错误分布等, 它在机器翻译研究和应用中起着重要作用。该文将人工译后编辑与错误分析结合起来, 对译后编辑操作进行错误标注, 采用自动标注和人工标注相结合的方法, 构建了一个细粒度英汉机器翻译错误分析语料库, 其中每一个标注样本包括源语言句子、机器译文、人工参考译文、译后编辑译文、词错误率和错误类型标注;标注的错误类型包括增词、漏词、错词、词序错误、未译和命名实体翻译错误等。标注的一致性检验表明了标注的有效性;对标注语料的统计分析结果能有效地指导机器翻译系统的开发和人工译员的后编辑。

Machine Translation

A Deep Insight into Measuring Face Image Utility with General and Face-specific Image Quality Metrics

no code implementations21 Oct 2021 Biying Fu, Cong Chen, Olaf Henniger, Naser Damer

This paper focuses on face images and the measurement of face image utility with general and face-specific image quality metrics.

Face Recognition Image Quality Assessment

Pricing Energy Storage in Real-time Market

no code implementations25 Jan 2021 Cong Chen, Lang Tong, Ye Guo

It is also shown that such settlements give rise to disincentives for generating firms and storage participants to bid truthfully, even when these market participants are rational price-takers in a competitive market.

Regioned Episodic Reinforcement Learning

no code implementations1 Jan 2021 Jiarui Jin, Cong Chen, Ming Zhou, Weinan Zhang, Rasool Fakoor, David Wipf, Yong Yu, Jun Wang, Alex Smola

Goal-oriented reinforcement learning algorithms are often good at exploration, not exploitation, while episodic algorithms excel at exploitation, not exploration.

Temporal Self-Ensembling Teacher for Semi-Supervised Object Detection

1 code implementation13 Jul 2020 Cong Chen, Shouyang Dong, Ye Tian, Kunlin Cao, Li Liu, Yuanhao Guo

(1) The teacher model serves a dual role as a teacher and a student, such that the teacher predictions on unlabeled images may be very close to those of student, which limits the upper-bound of the student.

Knowledge Distillation Object Detection +3

HOTCAKE: Higher Order Tucker Articulated Kernels for Deeper CNN Compression

no code implementations28 Feb 2020 Rui Lin, Ching-Yun Ko, Zhuolun He, Cong Chen, Yuan Cheng, Hao Yu, Graziano Chesi, Ngai Wong

The emerging edge computing has promoted immense interests in compacting a neural network without sacrificing much accuracy.

Edge-computing Fine-tuning +1

Kernelized Support Tensor Train Machines

no code implementations2 Jan 2020 Cong Chen, Kim Batselier, Wenjian Yu, Ngai Wong

In this paper, we propose a tensor train (TT)-based kernel technique for the first time, and apply it to the conventional support vector machine (SVM) for image classification.

Image Classification

Pricing Multi-Interval Dispatch under Uncertainty Part I: Dispatch-Following Incentives

no code implementations13 Nov 2019 Ye Guo, Cong Chen, Lang Tong

Part I investigates dispatch-following incentives of profit-maximizing generators and shows that, under mild conditions, no uniform-pricing scheme for the rolling-window economic dispatch provides dispatch-following incentives that avoid discriminative out-of-the-market uplifts.

Matrix Product Operator Restricted Boltzmann Machines

no code implementations12 Nov 2018 Cong Chen, Kim Batselier, Ching-Yun Ko, Ngai Wong

This work presents the matrix product operator RBM (MPORBM) that utilizes a tensor network generalization of Mv/TvRBM, preserves input formats in both the visible and hidden layers, and results in higher expressive power.

Denoising Dimensionality Reduction +1

Deep Compression of Sum-Product Networks on Tensor Networks

no code implementations9 Nov 2018 Ching-Yun Ko, Cong Chen, Yuke Zhang, Kim Batselier, Ngai Wong

Sum-product networks (SPNs) represent an emerging class of neural networks with clear probabilistic semantics and superior inference speed over graphical models.

Tensor Networks

A Support Tensor Train Machine

no code implementations17 Apr 2018 Cong Chen, Kim Batselier, Ching-Yun Ko, Ngai Wong

There has been growing interest in extending traditional vector-based machine learning techniques to their tensor forms.

Hybrid Dirac Semimetal in CaAgBi Materials Family

no code implementations13 Jun 2017 Cong Chen, Shan-Shan Wang, Lei Liu, Zhi-Ming Yu, Xian-Lei Sheng, Ziyu Chen, Shengyuan A. Yang

Based on their formation mechanisms, Dirac points in three-dimensional systems can be classified as accidental or essential.

Materials Science

Cannot find the paper you are looking for? You can Submit a new open access paper.