检索结果-南通市图书馆

Progress in Machine Translation

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Engineering 2022年第11期18卷 143-153页

作者： Haifeng Wang Hua Wu Zhongjun He Liang Huang Kenneth Ward Church baidu inc. Beijing 100193China baidu Research SunnyvaleCA 94089USA

After more than 70 years of evolution,great achievements have been made in machine *** in recent years,translation quality has been greatly improved with the emergence of neural machine translation(NMT).In this article,we first review the history of machine translation from rule-based machine translation to example-based machine translation and statistical machine *** then introduce NMT in more detail,inc.uding the basic framework and the current dominant framework,Transformer,as well as multilingual translation models to deal with the data sparseness *** addition,we introduce cutting-edge simultaneous translation methods that achieve a balance between translation quality and *** then describe various products and applications of machine *** the end of this article,we briefly discuss challenges and future research directions in this field.

关键词： Machine translation Neural machine translation Simultaneous translation

维普期刊数据库

Learning to Combine Answer Boundary Detection and Answer Re-ranking for Phrase-Indexed Question Answering

在线全文

学校读者我要写书评

暂无评论

Chinese Journal of Electronics 2022年第5期31卷 938-948页

作者： WEN Liang SHI Haibo ZHANG Xiaodong SUN Xin WEI Xiaochi WANG Junfeng CHENG Zhicong YIN Dawei WANG Xiaolin LUO Yingwei WANG Houfeng Department of Computer Science and Technology Peking University Peng Cheng Laboratory baidu inc.

Phrase-indexed question answering(PIQA) seeks to improve the inference speed of question answering(QA) models by enforcing complete independence of the document encoder from the question encoder,and it shows that the constrained model can achieve significant efficiency at the cost of its accuracy. In this paper, we aim to build a model under the PIQA constraint while reducing its accuracy gap with the unconstrained QA models. We propose a novel framework —Ans DR,which consists of an answer boundary detector(Ans D)and an answer candidate ranker(Ans R). More specifically, Ans D is a QA model under the PIQA architecture and it is designed to identify the rough answer boundaries; and Ans R is a lightweight ranking model to finely rerank the potential candidates without losing the efficiency. We perform the extensive experiments on public datasets. The experimental results show that the proposed method achieves the state of the art on the PIQA task.

关键词： text analysis unconstrained QA models Answer Re-ranking rough answer boundaries phrase-indexed question answering indexing lightweight ranking model information retrieval combine answer boundary detection question encoder natural language processing answer boundary detector QA model learning (artificial intelligence) encoding question answering (information retrieval) question answering models constrained model answer candidate ranker

How does working from home affect developer productivity?——A case study of baidu during the COVID-19 pandemic

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2022年第4期65卷 141-155页

作者： Lingfeng BAO Tao LI Xin XIA Kaiyu ZHU Hui LI Xiaohu YANG College of Computer Science and Technology Zhejiang University baidu inc. Faculty of Information Technology Monash University

Nowadays, working from home(WFH) has become a popular work arrangement due to its many potential benefits for both companies and employees(e.g., inc.easing job satisfaction and retention of employees). Many previous studies have investigated the impact of WFH on the productivity of ***, most of these studies usually use a qualitative analysis method such as surveys and interviews,and the studied participants do not work from home for a long continuing time. Due to the outbreak of coronavirus disease 2019(COVID-19), a large number of companies asked their employees to work from home, which provides us an opportunity to investigate whether WFH affects their productivity. In this study, to investigate the difference in developer productivity between WFH and working onsite, we conduct a quantitative analysis based on a dataset of developers’ daily activities from baidu inc., one of the largest IT companies in China. In total, we collected approximately four thousand records of 139 developers’ activities of 138 working days. Out of these records, 1103 records are submitted when developers work from home due to the COVID-19 pandemic. We find that WFH has both positive and negative impacts on developer productivity in terms of different metrics, e.g., the number of builds/commits/code reviews. We also notice that WFH has different impacts on projects with different characteristics inc.uding programming language,project type/age/size. For example, WFH has a negative impact on developer productivity for large ***, we find that productivity varies for different developers. Based on these findings, we get some feedback from developers of baidu and understand some reasons why WFH has different impacts on developer productivity. We also conclude several implications for both companies and developers.

关键词： WFH Developer Productivity developer productivity

同方期刊数据库

Bigflow: A General Optimization Layer for Distributed Computing Frameworks

在线全文

学校读者我要写书评

暂无评论

Journal of Computer Science & Technology 2020年第2期35卷 453-467页

作者： Yun-Cong Zhang Xiao-Yang Wang Cong Wang Yao Xu Jian-Wei Zhang Xiao-Dong Lin Guang-Yu Sun Gong-Lin Zheng Shan-Hui Yin Xian-Jin Ye Li Li Zhan Song Dong-Dong Miao baidu inc. Beijing 100193China Center for Energy-Efficient Computing and Applications Peking UniversityBeijing 100871China

As data volumes grow rapidly, distributed computations are widely employed in data-centers to provide cheap and efficient methods to process large-scale parallel datasets. Various computation models have been proposed to improve the abstraction of distributed datasets and hide the details of parallelism. However, most of them follow the single-layer partitioning method, which limits developers to express a multi-level partitioning operation succinc.ly. To overcome the problem, we present the NDD (Nested Distributed Dataset) data model. It is a more compact and expressive extension of Spark RDD (Resilient Distributed Dataset), in order to remove the burden on developers to manually write the logic for multi-level partitioning cases. Base on the NDD model, we develop an open-source framework called Bigflow, which serves as an optimization layer over computation engines from most widely used processing frameworks. With the help of Bigflow, some advanced optimization techniques, which may only be applied by experienced programmers manually, are enabled automatically in a distributed data processing job. Currently, Bigflow is processing about 3 PB data volumes daily in the data-centers of baidu. According to customer experience, it can significantly save code length and improve performance over the intuitive programming style.

关键词： distributed computing programming model optimization technique

A narrative review of glaucoma screening from fundus images

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Annals of Eye Science 2021年第3期6卷 45-58页

作者： Xingxing Cao Xu Sun Shuai Yan Yanwu Xu Intelligent Healthcare Unit Baidu Inc.BeijingChina

The objective of the paper is to provide a general view for automatic cup to disc ratio(CDR)assessment in fundus *** for the cause of blindness,glaucoma ranks as the second in ocular *** loss caused by glaucoma cannot be reversed,but the loss may be avoided if screened in the early stage of ***,early screening of glaucoma is very requisite to preserve vision and maintain quality of *** nerve head(ONH)assessment is a useful and practical technique among current glaucoma screening *** CDR as one of the clinical indicators for ONH assessment,has been well-used by clinicians and professionals for the analysis and diagnosis of *** key for automatic calculation of vertical CDR in fundus images is the segmentation of optic cup(OC)and optic disc(OD).We take a brief description of methodologies about the OC and disc optic segmentation and comprehensively presented these methods as two aspects:hand-craft feature and deep learning *** window regression,super-pixel level,image reconstruction,super-pixel level low-rank representation(LRR),deep learning methodologies for segmentation of OD and OC have been *** is hoped that this paper can provide guidance and bring inspiration to other *** mentioned method has its advantages and *** method should be selected or explored according to the actual *** automatic glaucoma screening,CDR is just the reflection for a small part of the disc,while utilizing comprehensive factors or multimodal images is the promising future direction to furthermore enhance the performance.

关键词： Glaucoma screening fundus images segmentation

A Survey of Multimodal Controllable Diffusion Models

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Computer Science & Technology 2024年第3期39卷 509-541页

作者：江锐郑光聪李藤杨天瑞王井东李玺 College of Computer Science and Technology Zhejiang UniversityHangzhou310007China Department of Mathematics Nanjing UniversityNanjing 210023China baidu Visual Technology Department Baidu Inc.Beijing 100085China IEEE

Diffusion models have recently emerged as powerful generative models,producing high-fidelity samples across *** this,they have two key challenges,inc.uding improving the time-consuming iterative generation process and controlling and steering the generation *** surveys provide broad overviews of diffusion model ***,they lack comprehensive coverage specifically centered on techniques for controllable *** survey seeks to address this gap by providing a comprehensive and coherent review on controllable generation in diffusion *** provide a detailed taxonomy defining controlled generation for diffusion *** generation is categorized based on the formulation,methodologies,and evaluation *** enumerating the range of methods researchers have developed for enhanced control,we aim to establish controllable diffusion generation as a distinc. subfield warranting dedicated *** this survey,we contextualize recent results,provide the dedicated treatment of controllable diffusion model generation,and outline limitations and future *** demonstrate applicability,we highlight controllable diffusion techniques for major computer vision tasks *** consolidating methods and applications for controllable diffusion models,we hope to catalyze further innovations in reliable and scalable controllable generation.

关键词： diffusion model controllable generation application personalization

ECharts: A declarative framework for rapid construction of web-based visualization

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Visual Informatics 2018年第2期2卷 136-146页

作者： Deqing Li Honghui Mei Yi Shen Shuang Su Wenli Zhang Junting Wang Ming Zu Wei Chen baidu inc. China State Key Lab of CAD&CG Zhejiang UniversityChina

While there have been a dozen of authoring systems and programming toolkits for visual design and development,users who do not have programming skills,such as data analysts or interface designers,still may feel cumbersome to efficiently implement a web-based *** this paper,we present ECharts,an open-sourced,web-based,cross-platform framework that supports the rapid construction of interactive *** motivation is driven by three goals:easy-touse,rich built-in interactions,and high *** kernel of ECharts is a suite of declarative visual design language that customizes built-in chart *** underlying streaming architecture,together with a high-performance graphics renderer based on HTML5 canvas,enables the high expandability and performance of *** report the design,implementation,and applications of ECharts with a diverse variety of *** compare the utility and performance of ECharts with ***,HighCharts,and *** of the experiments demonstrate the efficiency and scalability of our *** the first release in June 2013,ECharts has iterated 63 versions,and attracted over 22,000 star counts and over 1700 related projects in the *** is regarded as a leading visualization development tool in the world,and ranks the third in the GitHub visualization tab.

关键词： Information visualization Web-based visualization

A sampling method based on forecasting and combinatorial optimization for high performance A/B testing

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Frontiers of Computer Science 2023年第6期17卷 183-185页

作者： Fan LI Tiancheng ZHANG Shengjia CUI Hengyu LIU Zhibin REN Donglin DI Xiao WANG Po ZHANG Ge YU College of Computer Science and Engineering Northeastern UniversityShenyang 110819China baidu Inc.Beijing 100193China

1 Introduction A/B testing[1]is a popular statistical method for many applications,especially,widely used by Internet companies for user experience *** sampling algorithm is an important part of A/B testing and has a critical impact on the performance of A/B *** are two challenges to achieving high performance in A/B testing.(1)The features of individuals being sampled change over time and the sampling results used for evaluation are valid only for a period of time.(2)The sampling methods in A/B testing require determining whether the two groups of samples have an identical distribution while Simple Random Sampling(SRS)has a different purpose,which only concerns whether the sample distribution is identical to the population.

关键词： testing individual performance

维普期刊数据库

TextFormer: A Query-based End-to-end Text Spotter with Mixed Supervision

在线全文

学校读者我要写书评

暂无评论

Machine Intelligence Research 2024年第4期21卷 704-717页

作者： Yukun Zhai Xiaoqiang Zhang Xiameng Qin Sanyuan Zhao Xingping Dong Jianbing Shen School of Computer Science Beijing Institute of TechnologyBeijing 100081China Department of Computer Vision Technology Baidu Inc.Beijing 100193China

End-to-end text spotting is a vital computer vision task that aims to integrate scene text detection and recognition into a unified *** methods heavily rely on region-of-interest(Rol)operations to extract local features and complex post-processing steps to produce final *** address these limitations,we propose TextFormer,a query-based end-to-end text spotter with a transformer ***,using query embedding per text instance,TextFormer builds upon an image encoder and a text decoder to learn a joint semantic understanding for multitask *** allows for mutual training and optimization of classification,segmentation and recognition branches,resulting in deeper feature sharing without sacrificing flexibility or ***,we design an adaptive global aggregation(AGG)module to transfer global features into sequential features for reading arbitrarilyshaped texts,which overcomes the suboptimization problem of Rol ***,potential corpus information is utilized from weak annotations to full labels through mixed supervision,further improving text detection and end-to-end text spotting *** experiments on various bilingual(i.e.,English and Chinese)benchmarks demonstrate the superiority of our *** on the TDA-ReCTS dataset,TextFormer surpasses the state-of-the-art method in terms of 1-NED by 13.2%.

关键词： End-to-end text spotting arbitrarily-shaped texts transformer mixed supervision multitask modeling.