检索结果-内蒙古大学图书馆

2016 IEEE Advanced Information Management,Communicates,Electronic and Automation Control Conference(IMCEC 2016)

作者： Jiuru Zhao Xinguang Li Xia Li Laboratory of Language Engineering and Computing Guangdong University of Foreign Studies

ISBN: (纸本)9781509001668

A questionnaire text mining model is built based on latent semantic analysis(LSA).Take open questionnaire as the research object and improve Latent Dirichlet Allocation(LDA) model according to the text characteristics,a BM25-LDA model is *** comparing the LDA model and BM25-LDA model on the open questionnaire text,we can verify that the performance of BM25-LDA mode is better than that of original LDA model.

关键词： LSA open questionnaire text mining model building

来源：评论

学校读者我要写书评

暂无评论

Student understanding of graph slope and area under a graph: A comparison of physics and nonphysics students

引用

Physical Review Physics Education Research 2018年第2期14卷 020109-020109页

作者： Ana Susac Andreja Bubic Elizabeta Kazotti Maja Planinic Marijan Palmovic Department of Applied Physics Faculty of Electrical Engineering and Computing University of Zagreb Unska 3 10000 Zagreb Croatia Department of Physics Faculty of Science University of Zagreb Bijenicka 32 10000 Zagreb Croatia Chair for Psychology Faculty of Humanities and Social Sciences University of Split Sinjska 2 21000 Split Croatia Laboratory for Psycholinguistic Research Department of Speech and Language Pathology University of Zagreb Borongajska cesta 83h 10000 Zagreb Croatia

Previous studies have identified physics students’ difficulties with graph slope and area under a graph in different contexts. In this study we compared physics and nonphysics (psychology) students’ understanding of graphs; i.e., we evaluated the effects of concept (graph slope vs area under graph), type of question (qualitative vs quantitative), and context (physics vs finance) on their scores, strategies, and eye-tracking data. All students solved questions about graph slope better than the questions about area under a graph. Psychology students scored rather low on the questions about area under a graph, and physics students spent more time on questions about area under a graph than on slope questions, indicating that understanding of area under a graph is quite a difficult concept that seems unlikely to develop spontaneously. Generally, physics students had comparable scores on the qualitative and quantitative questions, whereas psychology students solved qualitative questions much better. As expected, students’ scores and eye-tracking measures indicated that problems involving physics context were easier for physics students since they typically had higher scores and shorter total and axes viewing times for physics than finance questions. Some physics students may have transferred the concepts and techniques from physics to finance because they typically scored better than psychology students on the finance questions that were novel for both groups. Analysis of student strategies showed that physics students mostly relied on strategies learned in physics courses, with strong emphasis on the use of formulas, whereas psychology students mostly used common-sense strategies, as they did not know the physics formulas. The implications of the results for teaching and learning about graphs in physics courses are also discussed.

关键词： Concepts & principles Student preparation

来源：评论

学校读者我要写书评

暂无评论

An environment for sustainable research software in Germany and beyond: Current state, open challenges, and call for action

arXiv

引用

arXiv 2020年

作者： Anzt, Hartwig Bach, Felix Druskat, Stephan Löffler, Frank Loewe, Axel Renard, Bernhard Y. Seemann, Gunnar Struck, Alexander Achhammer, Elke Aggarwal, Piush Appel, Franziska Bader, Michael Brusch, Lutz Busse, Christian Chourdakis, Gerasimos Dabrowski, Piotr W. Ebert, Peter Flemisch, Bernd Friedl, Sven Fritzsch, Bernadette Funk, Maximilian D. Gast, Volker Goth, Florian Grad, Jean-Noël Hermann, Sibylle Hohmann, Florian Janosch, Stephan Kutra, Dominik Linxweiler, Jan Muth, Thilo Peters-Kottig, Wolfgang Rack, Fabian Raters, Fabian H.C. Rave, Stephan Reina, Guido Reißig, Malte Ropinski, Timo Schaarschmidt, Joerg Seibold, Heidi Thiele, Jan P. Uekerman, Benjamin Unger, Stefan Weeber, Rudolf Germany Innovative Computing Lab University of Tennessee KnoxvilleTN United States Department of English Studies Friedrich Schiller University Jena Germany Germany Department of Computer Science Humboldt-Universität zu Berlin Germany Heinz Nixdorf Chair for Distributed Information Systems Friedrich Schiller University Jena Germany Michael Stifel Center Jena Germany Center for Computation and Technology Louisiana State University Baton Rouge United States Germany Robert Koch Institute Berlin Germany Hasso Plattner Institute Faculty of Digital Engineering University of Potsdam Germany Institute for Experimental Cardiovascular Medicine University Heart Centre Freiburg Bad Krozingen Germany Faculty of Medicine University of Freiburg Freiburg Germany Matters of Activity. Image Space Material. Cluster of Excellence at Humboldt-Universität zu Berlin Germany Technische Universität München Germany Language Technology Lab Universität Duisburg-Essen Germany Germany Department of Informatics Technical University of Munich Germany Technische Universität Dresden Germany Deutsches Krebsforschungszentrum Heidelberg Germany Scientific Computing in Computer Science Technical University Munich Germany School of Computing Communication and Business Hochschule für Technik und Wirtschaft Berlin Germany Center for Bioinformatics Saar Saarland Informatics Campus Germany Institute for Modelling Hydraulic and Environmental Systems University of Stuttgart Germany Berlin Institute of Health Germany Scientific Computing Alfred Wegener Institute Helmholtz Center for Polar and Marine Research Bremerhaven Germany Max-Planck-Gesellschaft e.V. Institut für Theoretische Physik und Astrophysik Universität Würzburg Germany Institut für Computerphysik University of Stuttgart Germany University Library University of Stuttgart Germany Universität Bremen Germany Max Planck Institute of Molecular Cell Biology and Genetics Dresden Germany European Molecular Biology Laboratory Heidelb

Research software has become a central asset in academic research. It optimizes existing and enables new research methods, implements and embeds research knowledge, and constitutes an essential research product in itself. Research software must be sustainable in order to understand, replicate, reproduce, and build upon existing research or conduct new research effectively. In other words, software must be available, discoverable, usable, and adaptable to new needs, both now and in the future. Research software therefore requires an environment that supports sustainability. Hence, a change is needed in the way research software development and maintenance are currently motivated, incentivized, funded, structurally and infrastructurally supported, and legally treated. Failing to do so will threaten the quality and validity of research. In this paper, we identify challenges for research software sustainability in Germany and beyond, in terms of motivation, selection, research software engineering personnel, funding, infrastructure, and legal aspects. Besides researchers, we specifically address political and academic decision-makers to increase awareness of the importance and needs of sustainable research software practices. In particular, we recommend strategies and measures to create an environment for sustainable research software, with the ultimate goal to ensure that software-driven research is valid, reproducible and sustainable, and that software is recognized as a first class citizen in research. This paper is the outcome of two workshops run in Germany in 2019, at deRSE19 - the first International Conference of Research Software Engineers in Germany - and a dedicated DFG-supported follow-up workshop in Berlin. Copyright © 2020, The Authors. All rights reserved.

关键词： Software design

来源：评论

学校读者我要写书评

暂无评论

Coherence-based Automated Essay Scoring using Self-Attention

Coherence-based Automated Essay Scoring using Self-Attention

引用

第十七届全国计算语言学学术会议暨第六届基于自然标注大数据的自然语言处理国际学术研讨会(CCL 2018)

作者： Xia Li Minping Chen Jianyun Nie Zhenxing Liu Ziheng Feng Yingdan Cai Key Laboratory of Language Engineering and Computing Guangdong university of foreign studies Guangzh School of Information Science and Technology/School of Cyber Security Guangdong university of foreig Department of Computer Science and Operations Research University of montreal MontrealCanada

Automated essay scoring aims to score an essay automatically without any human *** methods heavily rely on manual feature engi-neering,making it expensive to extract the *** recent studies used neural-network-based scoring models to avoid feature *** of them used CNN or RNN to learn the representation of the *** these mod-els can cope with relationships between words within a short distance,they are limited in capturing long-distance relationships across *** particular,it is difficult to assess the coherence of the essay,which is an essential criterion in essay *** this paper,we use self-attention to capture useful long-distance relationships between words so as to estimate a coherence *** tested our model on two datasets(ASAP and a new non-native speaker dataset).In both cases,our model outperforms the existing state-of-the-art models.

关键词： Self-Attention Automated Essay Scoring Neural Networks

来源：评论

学校读者我要写书评

暂无评论

Improvements on deep bottleneck network based i-vector representation for spoken language identification

Improvements on deep bottleneck network based i-vector repre...

引用

Speaker and language Recognition Workshop, Odyssey 2016

作者： Song, Yan Cui, Rui-Lian McLoughlin, Ian Dai, Li-Rong National Engineering Laboratory of Speech and Language Information Processing University of Science and Technology of China China National Engineering Laboratory of Speech and Language Information Processing School of Computing University of Kent Medway United Kingdom

Recently, the i-vector representation based on deep bottleneck networks (DBN) pre-trained for automatic speech recognition has received significant interest for both speaker verification (SV) and language identification (LID). In particular, a recent unified DBN based i-vector framework, referred to as DBN-pGMM i-vector, has performed well. In this paper, we replace the pGMM with a phonetic mixture of factor analyzers (pMFA), and propose a new DBN-pMFA i-vector. The DBN-pMFA i-vector includes the following improvements: (i) a pMFA model is derived from the DBN, which can jointly perform feature dimension reduction and de-correlation in a single linear transformation, (ii) a shifted DBF, termed SDBF, is proposed to exploit the temporal contextual information, (iii) a senone selection scheme is proposed to improve the i-vector extraction efficienvy. We evaluate the proposed DBN-pMFA i-vector on the most confused six languages selected from NIST LRE 2009. The experimental results demonstrate that DBN-pMFA can consistently outperform the previous DBN based framework [1]. The computational complexity can be significantly reduced by applying a simple senone selection scheme. © Odyssey 2016: Speaker and language Recognition Workshop. All rights reserved.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

LID-senone extraction via deep neural networks for end-to-end language identification

LID-senone extraction via deep neural networks for end-to-en...

引用

Speaker and language Recognition Workshop, Odyssey 2016

作者： Jin, Ma Song, Yan McLoughlin, Ian Dai, Li-Rong Ye, Zhong-Fu National Engineering Laboratory of Speech and Language Information Processing University of Science and Technology of China China School of Computing University of Kent Medway United Kingdom State Key Laboratory of Mathematical Engineering and Advanced Computing China

A key problem in spoken language identification (LID) is how to effectively model features from a given speech utterance. Recent techniques such as end-to-end schemes and deep neural networks (DNNs) utilising transfer learning such as bottleneck (BN) features, have demonstrated good overall performance, but have not addressed the extraction of LID-specific features. We thus propose a novel end-to-end neural network which aims to obtain effective LID-senone representations, which we define as being analogous to senones in speech recognition. We show that LID-senones combine a compact representation of the original acoustic feature space with a powerful descriptive and discriminative capability. Furthermore, a novel incremental training method is proposed to extract the weak language information buried in the acoustic features of insufficient language resources. Results on the six most confused languages in NIST LRE 2009 show good performance compared to state-of-the-art BN-GMM/i-vector and BN-DNN/i-vector systems. The proposed end-to-end network, coupled with an incremental training method which mitigates against over-fitting, has potential not just for LID, but also for other resource constrained tasks. © Odyssey 2016: Speaker and language Recognition Workshop. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Natural-Annotation-based Unsupervised Construction of Korean-Chinese Domain Dictionary

引用

IOP Conference Series: Materials Science and engineering 2018年第5期322卷

作者： Wuying Liu Lin Wang Laboratory of Language Engineering and Computing Guangdong University of Foreign Studies Guangzhou 510420 Guangdong China Xianda College of Economics and Humanities Shanghai International Studies University Shanghai 200083 China

The large-scale bilingual parallel resource is significant to statistical learning and deep learning in natural language processing. This paper addresses the automatic construction issue of the Korean-Chinese domain dictionary, and presents a novel unsupervised construction method based on the natural annotation in the raw corpus. We firstly extract all Korean-Chinese word pairs from Korean texts according to natural annotations, secondly transform the traditional Chinese characters into the simplified ones, and finally distill out a bilingual domain dictionary after retrieving the simplified Chinese words in an extra Chinese domain dictionary. The experimental results show that our method can automatically build multiple Korean-Chinese domain dictionaries efficiently.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Research of Improved Algorithm for GMM Voiceprint Recognition Model

A Research of Improved Algorithm for GMM Voiceprint Recognit...

引用

第28届中国控制与决策会议

作者： Zhang Jing Chen Xiao-mei Cisco School of Information Guangdong University of Foreign Studies Laboratory of Language Engineering and Computing Guangdong University of Foreign Studies

ISBN: (纸本)9781467397155

As an economical,reliable,easy and safe way to recognize identity,the Voiceprint recognition has a bright prospect in the market at ***,the bad robustness in a noisy environment constraints its practical application,so the key make voiceprint recognition be applied widely is to improve the robustness of system.A Voiceprint recognition system is mainly made up of signal recognition,feature extraction,model building and matching currently,the study to improve the recognition rate is mainly based the technology just *** paper studied a method to improve the systemrobustness by imp roving the voiceprint *** GMM is text-independent model and used *** order to improve the system recognition rate,this paper improved GMM model during training and recognition period *** training period,a k-means algorithm based on adjacent rules was put forward to obtain initial GM M value,which overcame the flaw that the system employs poor overall performance due to excessive attention on several indicators by the conventional *** increased training speed and recognition rate by virtue of simplifying the derivative process of *** recognition period,in order to avoid the influence of bad frames on the final result,a frame matchingweight method based on entropy was *** experiment result shown that improved GMM model effectively increased the robustness of voiceprint recognition system.

关键词： GMM Model Robustness EM Algorithm Entropy Matching Weight

来源：评论

学校读者我要写书评

暂无评论

The Application of Data Mining in Sports Events

The Application of Data Mining in Sports Events

引用

2016 2nd International Conference on Electronics,Network and Computer engineering(ICENCE 2016)

作者： Jiao Yu-ping Li Xia Physical Education Department Guangdong University of Foreign Studies Laboratory of Language Engineering and Computing Guangdong University of Foreign Studies

ISBN: (纸本)9781510830073

In recent years, data mining has played a more and more important role in all fields and had an increasingly greater influence. By using association analysis of data mining and classification algorithm, this paper analyzes the result data of volleyball games, which were held in a university's volleyball venue during 2010 Guangzhou Asian Games. It studies the correlation between different competing countries, competition time and audience number and make correlation analysis between the competition results and athletes' physical qualities. These results may be significant for scientific game guidance and athlete selection.

关键词： Data mining The Asian Games Volleyball Correlation analysis

来源：评论

学校读者我要写书评

暂无评论

A research of improved algorithm for GMM voiceprint recognition model 28

A research of improved algorithm for GMM voiceprint recognit...

引用

28th Chinese Control and Decision Conference, CCDC 2016

作者： Jing, Zhang Chen, Xiao-Mei Cisco School of Information Guangdong University of Foreign Studies Guangzhou510420 China Laboratory of Language Engineering and Computing Guangdong University of Foreign Studies Guangzhou510420 China

ISBN: (纸本)9781467397148

As an economical, reliable, easy and safe way to recognize identity, the Voiceprint recognition has a bright prospect in the market at present. However, the bad robustness in a noisy environment constraints its practical application, so the key make voiceprint recognition be applied widely is to improve the robustness of system. A Voiceprint recognition system is mainly made up of signal recognition, feature extraction, model building and matching, currently, the study to improve the recognition rate is mainly based the technology just mentioned. The paper studied a method to improve the system robustness by improving the voiceprint model. The GMM is text-independent model and used widely. In order to improve the system recognition rate, this paper improved GMM model during training and recognition period respectively. During training period, a k-means algorithm based on adjacent rules was put forward to obtain initial GM M value, which overcame the flaw that the system employs poor overall performance due to excessive attention on several indicators by the conventional method. It increased training speed and recognition rate by virtue of simplifying the derivative process of EM. During recognition period, in orderto avoid the influence of bad frames on the final result, a frame matching weight method based on entropy was proposed. The experiment result shown that improved GMM model effectively increased the robustness of voiceprint recognition system. © 2016 IEEE.

关键词： EM Algorithm Entropy GMM Model Matching Weight Robustness

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：