检索结果-内蒙古大学图书馆

arXiv 2017年

作者： Rekabsaz, Navid Lupu, Mihai Hanbury, Allan Duque, Andres Institute of Software Technology and Interactive Systems TU WIEN ViennaA-1040 Austria Madrid28040 Spain

We explore the use of unsupervised methods in Cross-Lingual Word Sense Disambiguation (CL-WSD) with the application of English to Persian. Our proposed approach targets the languages with scarce resources (low-density) by exploiting word embedding and semantic similarity of the words in context. We evaluate the approach on a recent evaluation benchmark and compare it with the state-of-the-art unsupervised system (CO-Graph). The results show that our approach outperforms both the standard baseline and the CO-Graph system in both of the task evaluation metrics (Out-Of-Five and Best result). Copyright © 2017, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

software quality: The future of systems- and software development: 8th International Conference, SWQD 2016 vienna, Austria, January 18–21, 2016 Proceedings 8th

Software quality: The future of systems- and software develo...

引用

8th International Conference on software Quality Days, SWQD 2016

作者： Winkler, Dietmar Biffl, Stefan Bergsmann, Johannes Institute of Software Technology and Interactive Systems Vienna University of Technology Vienna Austria Software Quality Lab GmbH Linz Austria

来源：评论

学校读者我要写书评

暂无评论

A multiple-perspective analysis of doctoral interdisciplinarity 15

A multiple-perspective analysis of doctoral interdisciplinar...

引用

15th International Conference on Information technology Based Higher Education and Training, ITHET 2016

作者： Del Carmen Calatrava Moreno, Maria Kynclova, Petra Werthner, Hannes Electronic Commerce Group Institute of Software Technology and Interactive Systems Vienna University of Technology Austria Institute of Statistics and Mathematical Methods in Economics Vienna University of Technology Austria

ISBN: (纸本)9781509007783

Interdisciplinary and assessment initiatives are two parallel educational paradigms that are being increasingly implemented in higher education institutions. Our study combines these two paradigms in order to assess the significance and performance of factors and processes that facilitate interdisci-plinarity at the doctoral level. Using the 360-degree feedback methodology, we integrate the perspectives of different academic stakeholders in the assessment, namely students, post-doctoral researchers, professors, directors, visiting professors and research funding agencies. Therefore, this study not only provides a global assessment but also informative intermediate results, such as analyses on the alignment and discrepancies of stakeholders as well as the identification of priorities for improvement. This paper presents the development and implementation of this multiple-perspective assessment within an academic context and discusses the results of its application in a European faculty of computer science where several doctoral programs with different approaches to interdisciplinarity co-exist. © 2016 IEEE.

关键词： Application programs

来源：评论

学校读者我要写书评

暂无评论

Machine learning with dual process models 5

Machine learning with dual process models

引用

5th International Conference on Pattern Recognition Applications and Methods, ICPRAM 2016

作者： Klauninger, Bert Unger, Martin Eidenberger, Horst Institute for Interactive Media Systems Vienna University of Technology Vienna Austria

ISBN: (纸本)9789897581731

Similarity measurement processes are a core part of most machine learning algorithms. Traditional approaches focus on either taxonomic or thematic thinking. Psychological research suggests that a combination of both is needed to model human-like similarity perception adequately. Such a combination is called a Similarity Dual Process Model (DPM). This paper describes how to construct DPMs as a linear combination of existing measures of similarity and distance. We use generalisation functions to convert distance into similarity. DPMs are similar to kernel functions. Thus, they can be integrated into any machine learning algorithm that uses kernel ***, not all DPMs that can be formulated work equally well. Therefore we test classification performance in a real-world task: the detection of pedestrians in images. We assume that DPMs are only viable if they yield better classifiers than their constituting parts. In our experiments, we found DPM kernels that matched the performance of conventional ones for our data set. Eventually, we provide a construction kit to build such kernels to encourage further experiments in other application domains of machine learning. © Copyright 2016 by SCITEPRESS - Science and technology Publications, Lda. All rights reserved.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

引用

5th International Conference on Pattern Recognition Applications and Methods, ICPRAM 2016

作者： Klauninger, Bert Eidenberger, Horst Institute for Interactive Media Systems Vienna University of Technology Vienna Austria

ISBN: (纸本)9789897581731

Based on recent findings from the field of human similarity perception, we propose a dual process model (DPM) of taxonomic and thematic similarity assessment which can be utilised in machine learning applications. Taxonomic reasoning is related to predicate based measures (counting) whereas thematic reasoning is mostly associated with metric distances (measuring). We suggest a procedure that combines both processes into a single similarity kernel. For each feature dimension of the observational data, an optimal measure is selected by a Greedy algorithm: A set of possible measures is tested, and the one that leads to improved classification performance of the whole model is denoted. These measures are combined into a single SVM kernel by means of generalisation (converting distances into similarities) and quantisation (applying predicate based measures to interval scale data). We then demonstrate how to apply our model to a classification problem of MPEG-7 features from a test set of images. Evaluation shows that the performance of the DPM kernel is superior to those of the standard SVM kernels. This supports our theory that the DPM comes closer to human similarity judgment than any singular measure, and it motivates our suggestion to employ the DPM not only in image retrieval but also in related tasks. © Copyright 2016 by SCITEPRESS - Science and technology Publications, Lda. All rights reserved.

关键词： Image retrieval

来源：评论

学校读者我要写书评

暂无评论

Major variants of the SIS architecture pattern for collective intelligence systems 16

Major variants of the SIS architecture pattern for collectiv...

引用

21st European Conference on Pattern Languages of Programs, EuroPLoP 2016

作者： Musil, Angelika Musil, Juergen Biffl, Stefan Institute of Software Technology and Interactive Systems TU Wien Favoritenstrasse 9/188 Vienna1040 Austria

ISBN: (纸本)9781450340748

Collective Intelligence systems (CIS), such as social networking services, wikis, and media sharing platforms, access and harness the collective knowledge of connected people by providing a web-based environment to share, distribute, and retrieve topic- specific information in an efficient way. In order to design well-tailored CIS, software architects need a complete understanding about (1) architectural principles that all kinds of CIS have in common, and (2) system variants in the field. Thus to provide consolidated systematic knowledge of architectural commonalities and variations in the CIS domain, we present in this work five major pattern variants of CIS. We investigated a number of CIS in the field with focus on a detailed survey of existing variants among key architecture-significant principles based on previously identified basic concepts, principles, and characteristics of software architectures that all CIS have in common. The variants are identified along two dimensions with respect to the relationship between the key elements of artifacts and actor records across and within two layers of the system. © 2016 ACM.

关键词： software architecture

来源：评论

学校读者我要写书评

暂无评论

On marrying model-driven engineering and process mining: A case study in execution-based model profiling 6

On marrying model-driven engineering and process mining: A c...

引用

6th International Symposium on Data-Driven Process Discovery and Analysis, SIMPDA 2016

作者： Mazak, Alexandra Wimmer, Manuel Institute of Software Technology and Interactive Systems TU Wien Favoritenstrasse 9-11 Vienna1040 Austria

In model-driven engineering (MDE), models are mostly used in prescriptive ways for system engineering. While prescriptive models are indeed an important ingredient to realize a system, for later phases in the systems' lifecycles additional model types are beneficial to use. Unfortunately, current MDE approaches mostly neglect the information upstream in terms of descriptive models from operations to design, which would be highly needed to improve systems continuously. To tackle this limitation, we propose execution-based model profiling as a continuous process to improve prescriptive models at design-time through runtime information by incorporating knowledge in form of profiled metadata from event logs generated during the execution of a code model. For this purpose we combine techniques of process mining (PM) with runtime models of MDE. In the course of a case study, we implement a preliminary prototype of our framework based on a traffic light system example which shows the feasibility and benefits of our execution-based model profiling approach. © 2016, CEUR-WS. All rights reserved.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

Supervised entity tagger for indonesian labor strike tweets using oversampling technique and low resource features

引用

Telkomnika (Telecommunication Computing Electronics and Control) 2016年第4期14卷 1462-1471页

作者： Purwarianti, Ayu Madlberger, Lisa Ibrahim, Muhammad School of Electrical Engineering and Informatics Bandung Institute of Technology Jl. Ganesa No. 10 Bandung Indonesia Institute of Software Technology and Interactive Systems Vienna University of Technology Favoritenstrasse 9-11/188 ViennaA-1040 Austria Faculty of Computer Science University of Indonesia Kampus UI Depok16424 Indonesia

We propose an entity tagger for Indonesian tweets sent during labor strike events using supervised learning methods. The aim of the tagger is to extract the date, location and the person/organization involved in the strike. We use SMOTE (Synthetic Minority Oversampling Technique) as an oversampling technique and conducted several experiments using Twitter data to evaluate different settings with varying machine learning algorithms and training data sizes. In order to test the low resource features, we also conducted experiments for the system without employing the word list feature and the word normalization. Our results indicated that different treatment of different types of machine learning algorithms with low resource features can lead to a good accuracy score. Here, we tried Naïve Bayes, C4.5, Random Forest and SMO (Sequential Minimal Optimization) algorithms using Weka as the machine learning tools. For the Naïve Bayes, due to the data distribution based of the class probability, the best accuracy was achieved by removing data duplication. For C4.5 and Random Forest, SMOTE gave higher accuracy result compared to the original data and the data with data duplication removal. For SMO, there is no significant difference among various sizes of training data. © 2016 Universitas Ahmad Dahlan.

关键词： Supervised learning

来源：评论

学校读者我要写书评

暂无评论

Learning analytics to improve writing skills for young children – an holistic approach

引用

Journal of Research in Innovative Teaching and Learning 2017年第2期10卷 143-159页

作者： Steinhauer, Nina Gros, Michael Ebner, Martin Ebner, Markus Huppertz, Anneliese Cormann, Mike Biermeier, Susanne Burk, Lena Edtstadler, Konstanze Gabriel, Sonja Wintschnig, Martina Aspalter, Christian Martich, Susanne Landesinstitut für Pädagogik und Medien Saarbrücken Germany Department of Educational Technology Graz University of Technology Graz Austria Institute for Interactive Systems and Data Science Faculty of Computer Science and Biomedical Engineering Technische Universitat Graz Graz Austria School of Raeren Raeren Belgium Albert-Weisgerber School St Ingbert Germany Institute of Professionalisation in Early Childhood and Primary Teacher Education University College of Teacher Education Steiermark Graz Austria University College of Teacher Education Vienna/Krems Vienna Austria

Purpose: Due to the important role of orthography in society, the project called IDeRBlog presented in this paper created a web-based tool to motivate pupils to write text as well as to read and to comment on texts written by fellow students. In addition, IDeRBlog aims to improve student’s German orthography skills and supports teachers and parents with training materials for their students. The paper aims to discuss these issues. Design/methodology/approach: With the aid of learning analytics, the submitted text is analyzed and special feedback is given to the students so that they can try to correct the misspelled words themselves. The teachers as well as the parents are benefiting from the analysis and exercises suggested by the system. Findings: A recent study showed the efficiency of the system in form of an improvement of the students’ orthographic skills. Over a period of four months 70 percent of the students achieved a significant reduction of their spelling mistakes. Originality/value: IDeRBlog is an innovative approach to improving orthography skills combining blogging and new media with writing and practice. © 2017, Nina Steinhauer, Michael Gros, Martin Ebner, Markus Ebner, Anneliese Huppertz, Mike Cormann, Susanne Biermeier, Lena Burk, Konstanze Edtstadler, Sonja Gabriel, Martina Wintschnig, Christian Aspalter and Susanne Martich.

关键词： German orthography German spelling acquisition Learning analytics technology enhanced learning

来源：评论

学校读者我要写书评

暂无评论

Truck circuits diagnosis for railway lines equipped with an automatic block signalling system

引用

IOP Conference Series: Materials Science and Engineering 2018年第1期294卷

作者： E Spunei I Piroi C Muscai E Răduca F Piroi Eftimie Murgu University of Resita Electrical Engineering and Informatics Department Traian Vuia str. no. 1-4 320085 Resita Romania Vienna University of Technology Institute of Software Technology and Interactive Systems Viena Austria

This work presents a diagnosis method for detecting track circuits failures on a railway traffic line equipped with an Automatic Block Signalling installation. The diagnosis method uses the installation's electrical schemas, based on which a series of diagnosis charts have been created. Further, the diagnosis charts were used to develop a software package, CDCBla, which substantially contributes to reducing the diagnosis time and human error during failure remedies. The proposed method can also be used as a training package for the maintenance staff. Since the diagnosis method here does not need signal or measurement inputs, using it does not necessitate additional IT knowledge and can be deployed on a mobile computing device (tablet, smart phone).

关键词：

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：