检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Kouni, Vasiliki Paraskevopoulos, Georgios Rauhut, Holger Alexandropoulos, George C. Kouni, Vicky Dep. of Informatics and Telecommunications National & Kapodistrian University of Athens Greece Mathematics of Information Processing RWTH Aachen University Germany School of Electrical & Computer Engineering National Technical University of Athens Greece Institute for Language & Speech Processing Athena Research Center Athens Greece

In this paper, we propose a new deep unfolding neural network based on the ADMM algorithm for analysis Compressed Sensing. The proposed network jointly learns a redundant analysis operator for sparsification and reconstructs the signal of interest. We compare our proposed network with a state-of-the-art unfolded ISTA decoder, that also learns an orthogonal sparsifier. Moreover, we consider not only image, but also speech datasets as test examples. Computational experiments demonstrate that our proposed network outperforms the state-of-the-art deep unfolding network, consistently for both real-world image and speech datasets. © 2021, CC BY.

关键词： Compressed sensing

来源：评论

学校读者我要写书评

暂无评论

"Take me Home": AR to connect exhibits to excavation sites

"Take me Home": AR to connect exhibits to excavation sites

引用

2020 AVI2CH Workshop on Advanced Visual Interfaces and Interactions in Cultural Heritage, AVI2CH 2020

作者： Antoniou, Angeliki Diakoumakos, Jason Lepouras, George Aggelakos, Yannis Kastritsis, Apostolos Platis, Nikos Department of Archival Library and Information Studies University of West Attica Aegaleo Greece Department of Informatics and Telecommunications University of the Peloponnese Tripolis Greece Yannis Aggelakos Creative Services Tripolis Greece Institute for Language and Speech Processing Athena Research and Innovation Centre Athens Greece

We present the design and implementation of an AR application that connects museum objects to their original locations in archaeological sites;our aim is both to solve the museum de-contextualization problem and to promote exploration of the archaeological sites in a region. The application projects the museum object upon the archaeological site and its original location, bringing the landscape into the museum experience. We outline technical challenges encountered and solutions adopted. Since this is a work in progress, further user testing remains to evaluate our approach and the app. © Copyright 2020 for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).

关键词： Augmented reality

来源：评论

学校读者我要写书评

暂无评论

Motion Capture of Modern Greek Verbs: Measuring aspects and relations among actions

Motion Capture of Modern Greek Verbs: Measuring aspects and ...

引用

IEEE Annual Conference on Pervasive Computing and Communications Workshops (Percom)

作者： Panagiotis Kouris Marietta Sionti Chrysovalantis Korfitis Stella Markantonatou School of Electrical & Computer Engineering National Technical University of Athens Greece Institute for Language and Speech Processing Athena RIC Greece

ISBN: (数字)9781728147161

ISBN: (纸本)9781728147178

In the context of human motion analysis and human-centered computational sensing, this work presents a methodology for the investigation of the relations among actions of a set of (Modern Greek) motion verbs. The actions denoted by these verbs fall in the motion categories of pushing, pulling, hitting, and beating. Motion data were collected with motion capture technology, and measures of correlation and distance are used to identify existing relations among actions. Finally, hierarchical clustering analysis was applied to identify groups of actions. The results are in line with a semantic categorization of the corresponding verbs. The overall experimental procedure and data analysis indicate that the employed methodology could be useful in promising applications of motion recognition or motion clustering, aiming at the identification of related captured actions.

关键词： Correlation Bones Feature extraction Three-dimensional displays Databases Measurement

来源：评论

学校读者我要写书评

暂无评论

The ILSP/Arc submission to the WMT 2018 Parallel Corpus Filtering Shared Task 3

The ILSP/ARC submission to the WMT 2018 Parallel Corpus Filt...

引用

3rd Conference on Machine Translation, WMT 2018 at the Conference on Empirical Methods in Natural language processing, EMNLP 2018

作者： Papavassiliou, Vassilis Prokopidis, Prokopis Sofianopoulos, Sokratis Piperidis, Stelios Institute for Language and Speech Processing Athena RC Athens Greece

ISBN: (纸本)9781948087810

This paper describes the submission of the institute for language and speech processing/athena Research and Innovation Center (ILSP/Arc) for the WMT 2018 Parallel Corpus Filtering shared task. We explore several properties of sentences and sentence pairs that our system explored in the context of the task with the purpose of clustering sentence pairs according to their appropriateness in training MT systems. We also discuss alternative methods for ranking the sentence pairs of the most appropriate clusters with the aim of generating the two datasets (of 10 and 100 million words as required in the task) that were evaluated. By summarizing the results of several experiments that were carried out by the organizers during the evaluation phase, our submission achieved an average BLEU score of 26.41, even though it does not make use of any language-specific resources like bilingual lexica, monolingual corpora, or MT output, while the average score of the best participant system was 27.91. ©2018 Association for Computational Linguistics

关键词： speech processing

来源：评论

学校读者我要写书评

暂无评论

UDALM: Unsupervised domain adaptation through language modeling

arXiv

引用

arXiv 2021年

作者： Karouzos, Constantinos Paraskevopoulos, Georgios Potamianos, Alexandros School of ECE National Technical University of Athens Athens Greece USC Los AngelesCA United States Behavioral Signal Technologies Los AngelesCA United States Institute for Language and Speech Processing Athena Research Center Athens Greece

In this work we explore Unsupervised Domain Adaptation (UDA) of pretrained language models for downstream tasks. We introduce UDALM, a fine-tuning procedure, using a mixed classification and Masked language Model loss, that can adapt to the target domain distribution in a robust and sample efficient manner. Our experiments show that performance of models trained with the mixed loss scales with the amount of available target data and the mixed loss can be effectively used as a stopping criterion during UDA training. Furthermore, we discuss the relationship between A-distance and the target error and explore some limitations of the Domain Adversarial Training approach. Our method is evaluated on twelve domain pairs of the Amazon Reviews Sentiment dataset, yielding 91.74% accuracy, which is an 1.11% absolute improvement over the state-of-the-art. Copyright © 2021, The Authors. All rights reserved.

关键词： Modeling languages

来源：评论

学校读者我要写书评

暂无评论

BIOMrc: A Dataset for biomedical machine reading comprehension

arXiv

引用

arXiv 2020年

作者： Stavropoulos, Petros Pappas, Dimitris Androutsopoulos, Ion McDonald, Ryan Department of Informatics Athens University of Economics and Business Greece Institute for Language and Speech Processing Research Center ‘Athena’ Greece Google Research

We introduce BIOMrc, a large-scale cloze-style biomedical Mrc dataset. Care was taken to reduce noise, compared to the previous BIOREAD dataset of Pappas et al. (2018). Experiments show that simple heuristics do not perform well on the new dataset, and that two neural Mrc models that had been tested on BIOREAD perform much better on BIOMrc, indicating that the new dataset is indeed less noisy or at least that its task is more feasible. Non-expert human performance is also higher on the new dataset compared to BIOREAD, and biomedical experts perform even better. We also introduce a new BERT-based Mrc model, the best version of which substantially outperforms all other methods tested, reaching or surpassing the accuracy of biomedical experts in some experiments. We make the new dataset available in three different sizes, also releasing our code, and providing a leaderboard. Copyright © 2020, The Authors. All rights reserved.

关键词： Large dataset

来源：评论

学校读者我要写书评

暂无评论

Privacy-preserving solutions in the Industrial Internet of Things

Privacy-preserving solutions in the Industrial Internet of T...

引用

International Conference on Distributed Computing in Sensor Systems (DCOSS)

作者： George Drosatos Konstantinos Rantos Dimitris Karampatzakis Thomas Lagkas Panagiotis Sarigiannidis Institute for Language and Speech Processing Athena Research Center Xanthi Greece Department of Computer Science International Hellenic University Kavala Greece Dept. of Electrical and Computer Engineering University of Western Macedonia Kozani Greece

ISBN: (数字)9781728143514

ISBN: (纸本)9781728198040

Industrial Internet of Things (IIoT) is a relatively new area of research that utilises multidisciplinary and holistic approaches to develop smart solutions for complex problems in industrial environments. Designing applications for the IIoT is a non trivial issue and requires to address, among many others, technology concerns, the protection of personal data, and the privacy of individuals. In this review paper, we identify privacy-preserving solutions that have been proposed in the literature to safeguard the privacy of individuals being part, or interacting with, the IIoT environment. As such, it considers two main categories of the analysed protocols, i.e., the privacy-preserving data management and processing solutions, and the privacy-preserving authentication methods.

关键词： Privacy Encryption Authentication

来源：评论

学校读者我要写书评

暂无评论

Deployment of LSTMs for real-time hand gesture interaction of 3D virtual music instruments with a leap motion sensor 15

Deployment of LSTMs for real-time hand gesture interaction o...

引用

15th Sound and Music Computing Conference, SMC 2018

作者： Kritsis, Kosmas Gkiokas, Aggelos Kaliakatsos-Papakostas, Maximos Katsouros, Vassilis Pikrakis, Aggelos Institute for Language and Speech Processing Athena Research and Innovation Center Greece Department of Informatics University of Piraeus Greece

ISBN: (纸本)9789963697304

The aim of this paper is to explore deep learning architectures for the development of a real-time gesture recognizer for the Leap Motion Sensor that will be able to continuously classify sliding windows into targeted gesture classes related to responsive interactions that are used in controlling the performance with a virtual 3D musical instrument. In terms of responsiveness it is assumed that the gestures can be recognized within a small time interval, while the employed gestures are inspired by interaction with realworld percussive and string instruments. The proposed method uses a Long Short-Term Memory (LSTM) network on top of a feature embedding layer of the raw data sequences as input, to map the input sequence to a vector of fixed dimensionality which is subsequently passed to a dense layer for classification among the targeted gesture classes. The performance evaluation of the proposed system has been carried out on a dataset of hand gestures of 8 classes with 11 participants. We report a recognition rate of 92.62% for a 10-fold cross-validation setup and 85.50% for a cross-participant setup. We also demonstrate that the later recognition rate can be further improved by adapting the trained model with the addition of few user gesture samples in the training set. © Proceedings of the 15th Sound and Music Computing Conference: Sonic Crossings, SMC 2018. All rights reserved.

关键词： Music

来源：评论

学校读者我要写书评

暂无评论

Fixed similes: Measuring aspects of the relation between MWE idiomatic semantics and syntactic flexibility 27

Fixed similes: Measuring aspects of the relation between MWE...

引用

Joint Workshop on Linguistic Annotation, Multiword Expressions and Constructions, LAW-MWECxG 2018, in conjunction with the 27th International Conference on Computational Linguistics, COLING 2018

作者： Markantonatou, Stella Kouris, Panagiotis Maistros, Yanis Institute for Language and Speech Processing Athena RIC Greece School of Electrical and Computer Engineering National Technical University of Athens Greece

ISBN: (纸本)9781948087513

We shed light on aspects of the relation between the semantics and the syntactic flexibility of multiword expressions (MWE) by investigating fixed adjective similes (FS), a predicative. MWE class not studied in this respect before. We work on Modern Greek data1 and find that only a subset of the observed syntactic structures is related with idiomaticity. We identify and measure two aspects of semantic idiomaticity, one of which seems to allow to predict FS syntactic flexibility. Our research draws on a resource developed with the semantic and detailed syntactic annotation of web-retrieved material, indicating frequency of use of the individual similes. Copyright © LAW-MWE-CxG 2018 - Joint Workshop on Linguistic Annotation, Multiword Expressions and Constructions, Proceedings of the *** rights reserved.

关键词： Syntactics

来源：评论

学校读者我要写书评

暂无评论

Embedding biomedical ontologies by jointly encoding network structure and textual node descriptors

arXiv

引用

arXiv 2019年

作者： Kotitsas, Sotiris Pappas, Dimitris Androutsopoulos, Ion McDonald, Ryan Apidianaki, Marianna Department of Informatics Athens University of Economics and Business Institute for Language and Speech Processing Research Center Athena Google Research CNRS LLF Univ. Paris France

Network Embedding (NE) methods, which map network nodes to low-dimensional feature vectors, have wide applications in network analysis and bioinformatics. Many existing NE methods rely only on network structure, overlooking other information associated with the nodes, e.g., text describing the nodes. Recent attempts to combine the two sources of information only consider local network structure. We extend NODE2VEC, a well-known NE method that considers broader network structure, to also consider textual node descriptors using recurrent neural encoders. Our method is evaluated on link prediction in two networks derived from UMLS. Experimental results demonstrate the effectiveness of the proposed approach compared to previous work. Copyright © 2019, The Authors. All rights reserved.

关键词： Network embeddings

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：