检索结果-内蒙古大学图书馆

arXiv 2018年

作者： Zhang, Zhuosheng He, Shexia Li, Zuchao Zhao, Hai Department of Computer Science and Engineering Shanghai Jiao Tong University Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University Shanghai200240 China

The goal of semantic role labeling (SRL) is to discover the predicate-argument structure of a sentence, which plays a critical role in deep processing of natural language. This paper introduces simple yet effective auxiliary tags for dependency-based SRL to enhance a syntax-agnostic model with multi-hop self-attention. Our syntax-agnostic model achieves competitive performance with state-of-the-art models on the CoNLL-2009 benchmarks both for English and Chinese. Copyright © 2018, The Authors. All rights reserved.

关键词： Syntactics

来源：评论

学校读者我要写书评

暂无评论

Subword-augmented embedding for cloze reading comprehension

arXiv

引用

arXiv 2018年

作者： Zhang, Zhuosheng Huang, Yafang Zhao, Hai Department of Computer Science and Engineering Shanghai Jiao Tong University Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University Shanghai200240 China

Representation learning is the foundation of machine reading comprehension. In state-of-the-art models, deep learning methods broadly use word and character level representations. However, character is not naturally the minimal linguistic unit. In addition, with a simple concatenation of character and word embedding, previous models actually give suboptimal solution. In this paper, we propose to use subword rather than character for word embedding enhancement. We also empirically explore different augmentation strategies on subword-augmented embedding to enhance the cloze-style reading comprehension model (reader). In detail, we present a reader that uses subword-level representation to augment word embedding with a short list to handle rare words effectively. A thorough examination is conducted to evaluate the comprehensive performance and generalization ability of the proposed reader. Experimental results show that the proposed approach helps the reader significantly outperform the state-of-the-art baselines on various public datasets. Copyright © 2018, The Authors. All rights reserved.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

An open science study of ageing in companion dogs (vol 602, g 51, 2022)

引用

NATURE 2022年第7924期608卷 E33-E33页

作者： Creevy, Kate E. Akey, Joshua M. Kaeberlein, Matt Promislow, Daniel E. L. Department of Small Animal Clinical Sciences Texas A&M University College of Veterinary Medicine & Biomedical Sciences College Station TX USA Lewis-Sigler Institute for Integrative Genomics Princeton University Princeton NJ USA Department of Laboratory Medicine and Pathology University of Washington School of Medicine Seattle WA USA Department of Biology University of Washington Seattle WA USA Institute for Stem Cell and Regenerative Medicine University of Washington Seattle WA USA Department of Clinical Microbiology and Immunology Sackler Faculty of Medicine Tel Aviv University Tel Aviv Israel Blavatnik School of Computer Science Tel Aviv University Tel Aviv Israel Santa Fe Institute Santa Fe NM USA Cornell Veterinary Biobank College of Veterinary Medicine Cornell University Ithaca NY USA Department of Sociology University of Washington Seattle WA USA Center for Studies in Demography and Ecology Seattle WA USA Department of Small Animal Medicine and Surgery University of Georgia College of Veterinary Medicine Athens GA USA Department of Veterinary Physiology and Pharmacology Texas A&M University College of Veterinary Medicine & Biomedical Sciences College Station TX USA Department of Family Medicine University of Washington Seattle WA USA Department of Epidemiology University of Washington Seattle WA USA Department of Global Health University of Washington Seattle WA USA Epidemiology Program Fred Hutchinson Cancer Research Center Seattle WA USA Department of Veterinary Pathobiology Texas A&M University College of Veterinary Medicine & Biomedical Sciences College Station TX USA Bioinformatics and Integrative Biology University of Massachusetts Chan Medical School Worcester MA USA Broad Institute of MIT and Harvard Cambridge MA USA Department of Biostatistics University of Washington Seattle WA USA Division of Public Health Sciences Fred Hutchinson Cancer Research Center Seattle WA USA Department of Population Health Sciences Vir

来源：评论

学校读者我要写书评

暂无评论

Accuracy Comparison of Spherical Parallel Manipulators Based on Joint Clearance 5

Accuracy Comparison of Spherical Parallel Manipulators Based...

引用

5th RSI International Conference on Robotics and Mechatronics, IcRoM 2017

作者： Mojtaba, Seyed Mousavi, Seyed Khoogar, Ahmadreza Masouleh, Mehdi Tale Mechanical Engineering Department Malek Ashtar University of Technology Tehran Iran Human and Robot Interaction Laboratory School of Electrical and Computer Engineering University of Tehran Iran

ISBN: (纸本)9781538657034

In this paper, three types of Spherical Parallel Manipulators (SPM) are compared from accuracy point of view based on joint clearances. The 3-RRR SPM is an overconstraint parallel mechanism and one can presume that it may exhibits an accurate motion. But beside the foregoing advantage, this structure has some drawbacks such as requiring high manufacturing precision and the difficulty of assembling the mechanism. Two other types, 3-RRS and 3-RSR, are non-overconstrained and do not have the above disadvantages, therefore these two types with 3- RRR are put into contrast from accuracy point of view. First, a method to obtain a model of moving platform pose (position and orientation) error is introduced which leads to a standard convex optimization problem. Since error calculation depends on the end-effector configuration, more than 1000 configurations are taken into account in order to cover SPMs workspaces. Then maximum values of six components of the pose error in each configuration are computed for each type. Finally, the three SPMs are compared based on maximum position and orientation error for given joint clearances. The obtained results revealed that the 3- RRR SPM has better position accuracy while in the case of orientation, the 3-RRS SPM has lowest maximum error between SPMs under study in the prescribed workspace. © 2017 IEEE.

关键词： Mechanisms

来源：评论

学校读者我要写书评

暂无评论

Finding Better Subword Segmentation for Neural Machine Translation

Finding Better Subword Segmentation for Neural Machine Trans...

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： Yingting Wu Hai Zhao Department of Computer Science and Engineering Shanghai Jiao Tong University Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong UniversityShanghai200240China

ISBN: (纸本)9783030017156

For different language pairs,word-level neural machine translation(NMT)models with a fixed-size vocabulary suffer from the same problem of representing out-of-vocabulary(OOV)*** common practice usually replaces all these rare or unknown words with a hUNKi token,which limits the translation performance to some *** of recent work handled such a problem by splitting words into characters or other specially extracted subword units to enable open-vocabulary *** pair encoding(BPE)is one of the successful attempts that has been shown extremely competitive by providing effective subword segmentation for NMT *** this paper,we extend the BPE style segmentation to a general unsupervised framework with three statistical measures: frequency(FRQ),accessor variety(AV)and description length gain(DLG).We test our approach on two translation tasks: German to English and Chinese to *** experimental results show that AV and DLG enhanced systems outperform the FRQ baseline in the frequency weighted schemes at different significant levels.

关键词： Neural machine translation Subword segmentation

来源：评论

学校读者我要写书评

暂无评论

Author Correction: Deciphering colorectal cancer genetics through multi-omic analysis of 100,204 cases and 154,587 controls of European and east Asian ancestries

引用

Nature genetics 2023年第3期55卷 519-520页

作者： Ceres Fernandez-Rozadilla Maria Timofeeva Zhishan Chen Philip Law Minta Thomas Stephanie Schmit Virginia Díez-Obrero Li Hsu Juan Fernandez-Tajes Claire Palles Kitty Sherwood Sarah Briggs Victoria Svinti Kevin Donnelly Susan Farrington James Blackmur Peter Vaughan-Shaw Xiao-Ou Shu Jirong Long Qiuyin Cai Xingyi Guo Yingchang Lu Peter Broderick James Studd Jeroen Huyghe Tabitha Harrison David Conti Christopher Dampier Mathew Devall Fredrick Schumacher Marilena Melas Gad Rennert Mireia Obón-Santacana Vicente Martín-Sánchez Ferran Moratalla-Navarro Jae Hwan Oh Jeongseon Kim Sun Ha Jee Keum Ji Jung Sun-Seog Kweon Min-Ho Shin Aesun Shin Yoon-Ok Ahn Dong-Hyun Kim Isao Oze Wanqing Wen Keitaro Matsuo Koichi Matsuda Chizu Tanikawa Zefang Ren Yu-Tang Gao Wei-Hua Jia John Hopper Mark Jenkins Aung Ko Win Rish Pai Jane Figueiredo Robert Haile Steven Gallinger Michael Woods Polly Newcomb David Duggan Jeremy Cheadle Richard Kaplan Timothy Maughan Rachel Kerr David Kerr Iva Kirac Jan Böhm Lukka-Pekka Mecklin Pekka Jousilahti Paul Knekt Lauri Aaltonen Harri Rissanen Eero Pukkala Johan Eriksson Tatiana Cajuso Ulrika Hänninen Johanna Kondelin Kimmo Palin Tomas Tanskanen Laura Renkonen-Sinisalo Brent Zanke Satu Männistö Demetrius Albanes Stephanie Weinstein Edward Ruiz-Narvaez Julie Palmer Daniel Buchanan Elizabeth Platz Kala Visvanathan Cornelia Ulrich Erin Siegel Stefanie Brezina Andrea Gsur Peter Campbell Jenny Chang-Claude Michael Hoffmeister Hermann Brenner Martha Slattery John Potter Konstantinos Tsilidis Matthias Schulze Marc Gunter Neil Murphy Antoni Castells Sergi Castellví-Bel Leticia Moreira Volker Arndt Anna Shcherbina Mariana Stern Bens Pardamean Timothy Bishop Graham Giles Melissa Southey Gregory Idos Kevin McDonnell Zomoroda Abu-Ful Joel Greenson Katerina Shulman Flavio Lejbkowicz Kenneth Offit Yu-Ru Su Robert Steinfelder Temitope Keku Bethany van Guelpen Thomas Hudson Heather Hampel Rachel Pearlman Sonja Berndt Richard Hayes Marie Elena Martinez Sushma Thomas Douglas Corley Paul Pharoah Susanna Larsson Yun Yen Heinz-Jo Edinburgh Cancer Research Centre Institute of Genomics and Cancer University of Edinburgh Edinburgh UK. Genomic Medicine Group Instituto de Investigacion Sanitaria de Santiago Santiago de Compostela Spain. Colon Cancer Genetics Group Medical Research Council Human Genetics Unit Institute of Genetics and Cancer University of Edinburgh Edinburgh UK. Danish Institute for Advanced Study Department of Public Health University of Southern Denmark Odense Denmark. Division of Epidemiology Department of Medicine Vanderbilt-Ingram Cancer Center Vanderbilt Epidemiology Center Vanderbilt University Medical Center Nashville TN USA. Division of Genetics and Epidemiology Institute of Cancer Research London UK. Public Health Sciences Division Fred Hutchinson Cancer Research Center Seattle WA USA. Genomic Medicine Institute Cleveland Clinic Cleveland OH USA. Population and Cancer Prevention Program Case Comprehensive Cancer Center Cleveland OH USA. Colorectal Cancer Group ONCOBELL Program Bellvitge Biomedical Research Institute Barcelona Spain. Oncology Data Analytics Program Catalan Institute of Oncology Barcelona Spain. Consortium for Biomedical Research in Epidemiology and Public Health Madrid Madrid Spain. Department of Clinical Sciences Faculty of Medicine University of Barcelona Barcelona Spain. Department of Biostatistics School of Public Health University of Washington Seattle WA USA. Institute of Cancer and Genomic Sciences College of Medical and Dental Sciences University of Birmingham Birmingham UK. Department of Public Health Richard Doll Building University of Oxford Oxford UK. Department of Biomedical Informatics Vanderbilt University School of Medicine Nashville TN USA. Department of Preventive Medicine USC Norris Comprehensive Cancer Center Keck School of Medicine University of Southern California Los Angeles CA USA. Center for Public Health Genomics Department of Public Health Sciences University of Virginia Charlottesville VA USA. De

来源：评论

学校读者我要写书评

暂无评论

Correction to: A multi-step genomic approach prioritized TBKBP1 gene as relevant for multiple sclerosis susceptibility

引用

Journal of neurology 2022年第8期269卷 4523-4524页

作者： Melissa Sorosina Nadia Barizzone Ferdinando Clarelli Santosh Anand Sara Lupoli Erika Salvi Eleonora Mangano Roberta Bordoni Tina Roostaei Elisabetta Mascia Miriam Zuccalà Domizia Vecchio Paola Cavalla Silvia Santoro Laura Ferrè Alen Zollo Cristina Barlassina Daniele Cusi Vittorio Martinelli Giancarlo Comi Maurizio Leone Massimo Filippi Nikolaos A Patsopoulos Philip L De Jager Gianluca De Bellis Federica Esposito Sandra D'Alfonso Filippo Martinelli Boneschi Laboratory of Human Genetics of Neurological Disorders Division of Neuroscience IRCCS San Raffaele Scientific Institute 20132 Milan Italy. Department of Health Sciences Interdisciplinary Research Center of Autoimmune Diseases (IRCAD) University of Eastern Piedmont Avogadro University 28100 Novara Italy. Department of Informatics Systems and Communications (DISCo) University of Milano-Bicocca Milan Italy. Department of Health Sciences University of Milan 20139 Milan Italy. Neuroalgology Unit Fondazione IRCCS Istituto Neurologico "Carlo Besta" 20133 Milan Italy. National Research Council of Italy Institute for Biomedical Technologies Segrate 20090 Milan Italy. Center for Translational and Computational Neuroimmunology Department of Neurology and the Taub Institute for Research On Alzheimer's Disease and the Aging Brain Columbia University Irving Medical Center New York NY 10032 USA. MS Centre SCDU Neurology AOU Maggiore Della Carità Department of Translational Medicine Interdisciplinary Research Center of Autoimmune Diseases (IRCAD) University of Eastern Piedmont Avogadro 28100 Novara Italy. MS Center Department of Neuroscience and Mental Health City of Health and Science University Hospital of Torino 10126 Turin Italy. Neurology Unit IRCCS San Raffaele Scientific Institute 20132 Milan Italy. Department of Pathophysiology and Transplantation (DEPT) Dino Ferrari Centre Neuroscience Section University of Milan 20122 Milan Italy. Bio4Dreams Business Nursery for Life Sciences Piazzale Principessa Clotilde 4/A 20121 Milan Italy. SC Neurologia Dipartimento Di Scienze Mediche IRCCS Casa Sollievo Della Sofferenza San Giovanni Rotondo Italy. Vita-Salute San Raffaele University 20132 Milan Italy. Neuroimaging Research Unit Division of Neuroscience IRCCS San Raffaele Scientific Institute 20132 Milan Italy. Neurophysiology Unit IRCCS San Raffaele Scientific Institute IRCCS San Raffaele Scientific Institute 20132 Milan Italy. Systems Biology and Comp

来源：评论

学校读者我要写书评

暂无评论

Flexible disaster response of tomorrow final presentation and evaluation of the CENTAURO system

arXiv

引用

arXiv 2019年

作者： Klamt, Tobias Rodriguez, Diego Baccelliere, Lorenzo Chen, Xi Chiaradia, Domenico Cichon, Torben Gabardi, Maßimiliano Guria, Paolo Holmquist, Karl Kamedula, Malgorzata Karaoguz, Hakan Kashiri, Navvab Laurenzi, Arturo Lenz, Christian Leonardis, Daniele Hoffman, Enrico Mingo Muratore, Luca Pavlichenko, Dmytro Porcini, Francesco Ren, Zeyu Schilling, Fabian Schwarz, Max Solazzi, Maßimiliano Felsberg, Michael Frisoli, Antonio Gustmann, Michael Jensfelt, Patric Nordberg, Klas Roßmann, Jürgen Süß, Uwe Tsagarakis, Nikos G. Behnke, Sven Autonomous Intelligent Systems University of Bonn Germany Humanoids and Human-Centred Mechatronics Istituto Italiano di Tecnologia Genoa Italy Department of Robotics Perception and Learning KTH Royal Institute of Technology Stockholm Sweden PERCRO Laboratory TeCIP Institute Sant'Anna School of Advanced Studies Pisa Italy Institute for Man-Machine Interaction RWTH Aachen University Germany Computer Vision Laboratory Linköping University Sweden Lausanne Switzerland Kerntechnische Hilfsdienst GmbH Karlsruhe Germany School of Electrical and Electronic Engineering University of Manchester United Kingdom

来源：评论

学校读者我要写书评

暂无评论

Evaluation of accessibility of university websites: A case from turkey 19th

Evaluation of accessibility of university websites: A case f...

引用

19th International Conference on human-computer interaction, HCI International 2017

作者： Yerlikaya, Zehra Durdu, Pınar Onay Department of Computer Engineering Graduate School of Natural and Applied Sciences Kocaeli University Izmit Kocaeli Turkey Computer Center Kocaeli University Izmit Kocaeli Turkey Department of Computer Engineering Faculty of Engineering Kocaeli University Izmit Kocaeli Turkey Human Computer Interaction Research Laboratory Kocaeli University Izmit Kocaeli Turkey

ISBN: (纸本)9783319587523

In this study, the accessibility of Turkish public universities website was analyzed to find the common accessibility issues that might detriment the users’ interaction. 20 public universities were randomly selected based on their URAP (University Ranking by Academic Performance) scores. Automated assessment was conducted by SortSite testing tool. According to the results, it was revealed that all of the websites have a number of accessibility conflicts with WCAG 2.0 criteria. It is worthy to note that there is no single university that fully satisfies the accessibility criteria. Most violations can be listed as missing text alternatives for non-text contents, missing helpful and clear page titles, unclear links, unassigned document main language, contrast violations or unclear labels. © Springer International Publishing AG 2017.

关键词： Websites

来源：评论

学校读者我要写书评

暂无评论

Multimodal emotion recognition using deep canonical correlation analysis

arXiv

引用

arXiv 2019年

作者： Liu, Wei Qiu, Jie-Lin Zheng, Wei-Long Lu, Bao-Liang Center for Brain-Like Computing and Machine Intelligence Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai200240 China Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University Shanghai200240 China Brain Science and Technology Research Center Shanghai Jiao Tong University Shanghai200240 China Department of Electronic Engineering Shanghai Jiao Tong University Shanghai200240 China Department of Neurology Massachusetts General Hospital Harvard Medical School BostonMA02114 United States

Multimodal signals are more powerful than unimodal data for emotion recognition since they can represent emotions more comprehensively. In this paper, we introduce deep canonical correlation analysis (DCCA) to multimodal emotion recognition. The basic idea behind DCCA is to transform each modality separately and coordinate different modalities into a hyperspace by using specified canonical correlation analysis constraints. We evaluate the performance of DCCA on five multimodal datasets: the SEED, SEED-IV, SEED-V, DEAP, and DREAMER datasets. Our experimental results demonstrate that DCCA achieves state-of-the-art recognition accuracy rates on all five datasets: 94.58% on the SEED dataset, 87.45% on the SEED-IV dataset, 84.33% and 85.62% for two binary classification tasks and 88.51% for a four-category classification task on the DEAP dataset, 83.08% on the SEED-V dataset, and 88.99%, 90.57%, and 90.67% for three binary classification tasks on the DREAMER dataset. We also compare the noise robustness of DCCA with that of existing methods when adding various amounts of noise to the SEED-V dataset. The experimental results indicate that DCCA has greater robustness. By visualizing feature distributions with t-SNE and calculating the mutual information between different modalities before and after using DCCA, we find that the features transformed by DCCA from different modalities are more homogeneous and discriminative across emotions. Copyright © 2019, The Authors. All rights reserved.

关键词： Eye movements

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：