Search

Your search keyword '"Zhang, Ruiqing"' showing total 641 results
Start Over Author "Zhang, Ruiqing"
641 results on '"Zhang, Ruiqing"'

2. An Empirical Study of Consistency Regularization for End-to-End Speech-to-Text Translation

Author

Gao, Pengzhi, Zhang, Ruiqing, He, Zhongjun, Wu, Hua, and Wang, Haifeng

Subjects
Computer Science - Computation and Language
Abstract

Consistency regularization methods, such as R-Drop (Liang et al., 2021) and CrossConST (Gao et al., 2023), have achieved impressive supervised and zero-shot performance in the neural machine translation (NMT) field. Can we also boost end-to-end (E2E) speech-to-text translation (ST) by leveraging consistency regularization? In this paper, we conduct empirical studies on intra-modal and cross-modal consistency and propose two training strategies, SimRegCR and SimZeroCR, for E2E ST in regular and zero-shot scenarios. Experiments on the MuST-C benchmark show that our approaches achieve state-of-the-art (SOTA) performance in most translation directions. The analyses prove that regularization brought by the intra-modal consistency, instead of modality gap, is crucial for the regular E2E ST, and the cross-modal consistency could close the modality gap and boost the zero-shot E2E ST performance.

Published
2023

10. Comparative Study on Flexible Power Sources for Renewable Energy Bases in High Altitude Arid Regions

Author

Shen, Zhan, Li, Xingyun, Bao, Weining, Wang, Jun, Zhang, Ruiqing, Zhang, Pengfei, Wang, Shunchao, Angrisani, Leopoldo, Series Editor, Arteaga, Marco, Series Editor, Chakraborty, Samarjit, Series Editor, Chen, Jiming, Series Editor, Chen, Shanben, Series Editor, Chen, Tan Kay, Series Editor, Dillmann, Rüdiger, Series Editor, Duan, Haibin, Series Editor, Ferrari, Gianluigi, Series Editor, Ferre, Manuel, Series Editor, Jabbari, Faryar, Series Editor, Jia, Limin, Series Editor, Kacprzyk, Janusz, Series Editor, Khamis, Alaa, Series Editor, Kroeger, Torsten, Series Editor, Li, Yong, Series Editor, Liang, Qilian, Series Editor, Martín, Ferran, Series Editor, Ming, Tan Cher, Series Editor, Minker, Wolfgang, Series Editor, Misra, Pradeep, Series Editor, Mukhopadhyay, Subhas, Series Editor, Ning, Cun-Zheng, Series Editor, Nishida, Toyoaki, Series Editor, Oneto, Luca, Series Editor, Panigrahi, Bijaya Ketan, Series Editor, Pascucci, Federica, Series Editor, Qin, Yong, Series Editor, Seng, Gan Woon, Series Editor, Speidel, Joachim, Series Editor, Veiga, Germano, Series Editor, Wu, Haitao, Series Editor, Zamboni, Walter, Series Editor, Tan, Kay Chen, Series Editor, Cai, Chunwei, editor, Qu, Xiaohui, editor, Mai, Ruikun, editor, Zhang, Pengcheng, editor, Chai, Wenping, editor, and Wu, Shuai, editor

Published
2024
Full Text
View/download PDF

18. BSTC: A Large-Scale Chinese-English Speech Translation Dataset

Author

Zhang, Ruiqing, Wang, Xiyang, Zhang, Chuanqiang, He, Zhongjun, Wu, Hua, Li, Zhi, Wang, Haifeng, Chen, Ying, and Li, Qinfei

Subjects
Computer Science - Computation and Language
Abstract

This paper presents BSTC (Baidu Speech Translation Corpus), a large-scale Chinese-English speech translation dataset. This dataset is constructed based on a collection of licensed videos of talks or lectures, including about 68 hours of Mandarin data, their manual transcripts and translations into English, as well as automated transcripts by an automatic speech recognition (ASR) model. We have further asked three experienced interpreters to simultaneously interpret the testing talks in a mock conference setting. This corpus is expected to promote the research of automatic simultaneous translation as well as the development of practical systems. We have organized simultaneous translation tasks and used this corpus to evaluate automatic simultaneous translation systems., Comment: 8 pages, 6 figures

Published
2021

28. DuTongChuan: Context-aware Translation Model for Simultaneous Interpreting

Author

Xiong, Hao, Zhang, Ruiqing, Zhang, Chuanqiang, He, Zhongjun, Wu, Hua, and Wang, Haifeng

Subjects
Computer Science - Computation and Language
Abstract

In this paper, we present DuTongChuan, a novel context-aware translation model for simultaneous interpreting. This model allows to constantly read streaming text from the Automatic Speech Recognition (ASR) model and simultaneously determine the boundaries of Information Units (IUs) one after another. The detected IU is then translated into a fluent translation with two simple yet effective decoding strategies: partial decoding and context-aware decoding. In practice, by controlling the granularity of IUs and the size of the context, we can get a good trade-off between latency and translation quality easily. Elaborate evaluation from human translators reveals that our system achieves promising translation quality (85.71% for Chinese-English, and 86.36% for English-Chinese), specially in the sense of surprisingly good discourse coherence. According to an End-to-End (speech-to-speech simultaneous interpreting) evaluation, this model presents impressive performance in reducing latency (to less than 3 seconds at most times). Furthermore, we successfully deploy this model in a variety of Baidu's products which have hundreds of millions of users, and we release it as a service in our AI platform., Comment: Description for Baidu's Simultaneous Interpreting System

Published
2019

32. The Position and Development of Dunhuang Art in The Torrent of World Culture

Author

Zhang, Ruiqing, Striełkowski, Wadim, Editor-in-Chief, Black, Jessica M., Series Editor, Butterfield, Stephen A., Series Editor, Chang, Chi-Cheng, Series Editor, Cheng, Jiuqing, Series Editor, Dumanig, Francisco Perlas, Series Editor, Al-Mabuk, Radhi, Series Editor, Scheper-Hughes, Nancy, Series Editor, Urban, Mathias, Series Editor, Webb, Stephen, Series Editor, Holl, Augustin, editor, Chen, Jun, editor, and Guan, Guiyun, editor

Published
2022
Full Text
View/download PDF

34. Effect of Electroacupuncture at Shenting and Baihui Acupoints on Superoxide Dismutase Activity and Malondialdehyde Content in the Brain Tissue in a Rat Model of Learning and Memory Impairment Induced by Cerebral Ischemia-reperfusion Injury

Author

Xiao YAN, LEE JAEMYUNG, Ming ZHANG, Ruiqing LI, Jing GAO, Xiaodong FENG

Subjects
brain ischemia, reperfusion injury, electroacupuncture, shenting, baihui, superoxide dismutase, malondialdehyde, memory disorders, models, animal, Medicine
Abstract

Background The use of electroacupuncture at Shenting and Baihui acupoints may improve the learning and memory impairment in cerebral ischemic stroke patients with cognitive impairment induced by one pathogenic factor known as abnormal free radical metabolism. Objective To explore the possible mechanism of using electroacupuncture at Shenting and Baihui acupoints to improve the learning and memory impairment in a rat model of cerebral ischemia-reperfusion induced learning and memory impairment by observing the changes of superoxide dismutase (SOD) activity and malondialdehyde (MDA) content in brain tissues of the model. Methods This experiment was conducted from August 2019 to August 2020. Eighteen SPF male SD rats were selected and equally randomized into three groups by use of random allocation using SPSS 22.0: sham operation group (receiving a neck incision for separating the neck artery, then being caught at a fixed time point), model group (receiving occlusion of the middle cerebral artery for inducing ischemia-reperfusion injury, then being assessed with a Zea-Longa score of 1-3 points in the fully awake state, and being caught at a fixed time point) and electroacupuncture group (first receiving interventions similar to those given to rats in the model group, then on the first day after being successfully modeled, receiving a 30-minute electroacupuncture at Shenting and Baihui acupoints with dense-sparse waves in the frequency range of 1 Hz/20 Hz, once daily, for two consecutive weeks). When the intervention ended, Morris water maze experiment was used to test the learning and memory ability of all rats. The SOD activity and MDA content in brain tissues of rats were measured by WST-1 assay, and thiobarbituric acid assay, respectively. Results The rats in both model group and electroacupuncture group were modeled successfully. On the 13th day of training trial, compared with rats in the sham operation group, those in the model group showed an increased escape latency and decreased number of crossing the platform (P

Published
2022
Full Text
View/download PDF

35. ERCP management of acute cholangitis caused by rupture of Echinococcus hepaticus into the biliary tract

Author

Jiang, Tiemin, Wang, Zongding, Aji, Tuerganaili, Ran, Bo, Guo, Qiang, Zhang, Ruiqing, Tuergan, Talaiti, Zhong, Kai, Shao, Yingmei, and Hao, Wen

Subjects
Endoscopic retrograde cholangiopancreatography, Methylene blue, Company business management, Health
Abstract

Byline: Tiemin. Jiang, Zongding. Wang, Tuerganaili. Aji, Bo. Ran, Qiang. Guo, Ruiqing. Zhang, Talaiti. Tuergan, Kai. Zhong, Yingmei. Shao, Wen. Hao Background: Hepatic cystic echinococcosis (HCE) rupture into the biliary [...]

Published
2023

40. Quasi-Steady State Time Model of Fire Smoke Transmission in Long-Narrow Spaces

Author

WANG Jinhui, HUANG Yijun, CUI Xin, ZHANG Shaogang, ZHANG Ruiqing

Subjects
fire smoke, long-narrow space, lag, quasi-steady state model, critical time, Engineering (General). Civil engineering (General), TA1-2040, Chemical engineering, TP155-156, Naval architecture. Shipbuilding. Marine engineering, VM1-989
Abstract

Transport time lag is a crucial characteristic of fire spreading in fire early stage, which determines the activation time of the fire detector. To clarify the quantitative relationship between the delay behavior and the quasi-steady state of smoke transmission in a long-narrow space, a time-varying spreadsheet is theoretically proposed to calculate the delay time of fire smoke transmission based on the theory of weak plume and the existing achievements concerned. Moreover, a theoretical model concerning the critical time for quasi-steady state assumption applicability is developed, where the method of calculating the critical time is also presented. The results of the case study show that due to the difference of smoke spreading velocity in long-narrow spaces and unconfined spaces for a case with the same conditions, the critical time for the smoke transmission to reach the quasi-steady state at a given radial distance on the ceiling in a long-narrow space is larger than that in the open space. For the open case, the thin ceiling plume, the small volume of entrained air, and the relatively high velocity of smoke lead to the longer delay time of smoke transmission in a long-narrow space than that in the open space under the same situations.

Published
2022
Full Text
View/download PDF

46. DeepTransport: Learning Spatial-Temporal Dependency for Traffic Condition Forecasting

Author

Cheng, Xingyi, Zhang, Ruiqing, Zhou, Jie, and Xu, Wei

Subjects
Computer Science - Artificial Intelligence
Abstract

Predicting traffic conditions has been recently explored as a way to relieve traffic congestion. Several pioneering approaches have been proposed based on traffic observations of the target location as well as its adjacent regions, but they obtain somewhat limited accuracy due to a lack of mining road topology. To address the effect attenuation problem, we suggest taking into account the traffic of surrounding locations(wider than the adjacent range). We propose an end-to-end framework called DeepTransport, in which Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN) are utilized to obtain spatial-temporal traffic information within a transport network topology. In addition, an attention mechanism is introduced to align spatial and temporal information. Moreover, we constructed and released a real-world large traffic condition dataset with a 5-minute resolution. Our experiments on this dataset demonstrate our method captures the complex relationship in the temporal and spatial domains. It significantly outperforms traditional statistical methods and a state-of-the-art deep learning method.

Published
2017

47. The Application of Biochar Derived from Rice Husk Enhanced the Bioremediation of Petroleum-Contaminated Soil in Semi-Arid Areas.

Author

Liu, Zhe, Zhang, Yang, Li, Xiumin, Sun, Zenghui, Zhang, Ruiqing, Li, Xuxiang, and Du, Yichun

Subjects
BIODEGRADATION of petroleum, ENVIRONMENTAL health, RICE hulls, SOIL microbiology, SOIL remediation
Abstract

With the continuous expansion of petroleum exploitation, a large amount of petroleum hydrocarbons has leaked into the Earth's soil, which seriously threatens ecological health. Hence, a series of experiments were conducted to evaluate the performance of natural attenuation (NA), rice husk (RH), and biochar derived from rice husk (RHBC) in enhancing the bioremediation of petroleum-contaminated soil. When the biodegradation time reached 100 d, the total petroleum hydrocarbons (TPHs) biodegradation amounts of NA, RH, and RHBC were 3688.2, 4557.9, and 5913.3 mg/kg, which was equal to the biodegradation efficiency of 32.8, 40.6, and 52.6%, respectively. Compared with NA and RH, the biodegradation efficiency of n-alkanes C11–C15 (C11 represents n-alkanes with 11 carbons, namely n-Hendecane) C16–C29, and C30–C40 in RHBC increased to 69.7~82.5%, 42.4~81.5%, and 30.2~48.1%, equivalent to 12.2~34.5%, 6.9~31.2%, and 13.5~37.1% more than NA and RH, respectively. Moreover, the half-life of biodegradation in RHBC was shorted to 83.3 d, equal to 49.7 and 67.9% of NA and RH, respectively. Furthermore, the application of RHBC could improve the dehydrogenase activity in soil and promote the growth and reproduction of petroleum-degrading bacteria (PDB), which enhances the biodegradation of petroleum hydrocarbons. This study exhibited that biochar formed from biomass pyrolysis is a potential biostimulator in enhancing the remediation of petroleum-contaminated soil by indigenous bacteria. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results