检索结果-内蒙古大学图书馆

Document-level neural machine translation with associated memory network

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Jiang, Shu Wang, Rui Li, Zuchao Utiyama, Masao Chen, Kehai Sumita, Eiichiro Zhao, Hai Lu, Bao-Liang Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai200240 China Key Lab. of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University Shanghai200240 China National Institute of Information and Communications Technology Kyoto-shi6190289 Japan

Standard neural machine translation (NMT) is on the assumption that the document-level context is independent. Most existing document-level NMT approaches are satisfied with a smattering sense of global document-level information, while this work focuses on exploiting detailed document-level context in terms of a memory network. The capacity of the memory network that detecting the most relevant part of the current sentence from memory renders a natural solution to model the rich document-level context. In this work, the proposed document-aware memory network is implemented to enhance the Transformer NMT baseline. Experiments on several tasks show that the proposed method significantly improves the NMT performance over strong Transformer baselines and other related studies. © 2019, CC BY.

关键词： Neural machine translation

The 2021 report of the Lancet Countdown on health and climate change: code red for a healthy future

学校读者我要写书评

暂无评论

The Lancet 2021年第10311期398卷 1619-1662页

作者： Romanello, Marina McGushin, Alice Di Napoli, Claudia Drummond, Paul Hughes, Nick Jamart, Louis Kennard, Harry Lampard, Pete Solano Rodriguez, Baltazar Arnell, Nigel Ayeb-Karlsson, Sonja Belesova, Kristine Cai, Wenjia Campbell-Lendrum, Diarmid Capstick, Stuart Chambers, Jonathan Chu, Lingzhi Ciampi, Luisa Dalin, Carole Dasandi, Niheer Dasgupta, Shouro Davies, Michael Dominguez-Salas, Paula Dubrow, Robert Ebi, Kristie L Eckelman, Matthew Ekins, Paul Escobar, Luis E Georgeson, Lucien Grace, Delia Graham, Hilary Gunther, Samuel H Hartinger, Stella He, Kehan Heaviside, Clare Hess, Jeremy Hsu, Shih-Che Jankin, Slava Jimenez, Marcia P Kelman, Ilan Kiesewetter, Gregor Kinney, Patrick L Kjellstrom, Tord Kniveton, Dominic Lee, Jason K W Lemke, Bruno Liu, Yang Liu, Zhao Lott, Melissa Lowe, Rachel Martinez-Urtaza, Jaime Maslin, Mark McAllister, Lucy McMichael, Celia Mi, Zhifu Milner, James Minor, Kelton Mohajeri, Nahid Moradi-Lakeh, Maziar Morrissey, Karyn Munzert, Simon Murray, Kris A Neville, Tara Nilsson, Maria Obradovich, Nick Sewe, Maquins Odhiambo Oreszczyn, Tadj Otto, Matthias Owfi, Fereidoon Pearman, Olivia Pencheon, David Rabbaniha, Mahnaz Robinson, Elizabeth Rocklöv, Joacim Salas, Renee N Semenza, Jan C Sherman, Jodi Shi, Liuhua Springmann, Marco Tabatabaei, Meisam Taylor, Jonathon Trinanes, Joaquin Shumake-Guillemot, Joy Vu, Bryan Wagner, Fabian Wilkinson, Paul Winning, Matthew Yglesias, Marisol Zhang, Shihui Gong, Peng Montgomery, Hugh Costello, Anthony Hamilton, Ian Institute for Global Health University College London London UK United Kingdom Institute for Sustainable Resources University College London London UK United Kingdom UCL Energy Institute University College London London UK United Kingdom Institute for Environmental Design and Engineering University College London London UK United Kingdom Department of Geography University College London London UK United Kingdom The Bartlett School of Sustainable Construction University College London London UK United Kingdom Centre for Human Health and Performance University College London London UK United Kingdom School of Agriculture Policy and Development University of Reading Reading United Kingdom Department of Meteorology University of Reading Reading United Kingdom The Walker Institute University of Reading Reading United Kingdom Department of Health Sciences University of York York United Kingdom Institute for Environment and Human Security United Nations University Bonn Germany Centre on Climate Change and Planetary Health London School of Hygiene & Tropical Medicine London UK United Kingdom Centre for Mathematical Modelling of Infectious Diseases London School of Hygiene & Tropical Medicine London UK United Kingdom Department of Public Health Environments and Society London School of Hygiene & Tropical Medicine London UK United Kingdom Department of Earth System Science Tsinghua University Beijing China Department of Environment Climate Change and Health World Health Organization Geneva Switzerland Institute for Environmental Sciences World Health Organization Geneva Switzerland Centre for Climate Change and Social Transformations School of Psychology Cardiff University Cardiff United Kingdom Yale Center on Climate Change and Health Yale University New Haven CT United States School of Government University of Birmingham Birmingham United Kingdom Economic analysis of Climate Impacts and Policy Centro Euro-Mediterraneo sui Cambiamenti Climatic

Neural response ranking for social conversation: A data-efficient approach

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Shalyminov, Igor Dušek, Ondřej Lemon, Oliver Interaction Lab Department of Computer Science Heriot-Watt University EdinburghEH14 4AS United Kingdom

The overall objective of 'social' dialogue systems is to support engaging, entertaining, and lengthy conversations on a wide variety of topics, including social chit-chat. Apart from raw dialogue data, user-provided ratings are the most common signal used to train such systems to produce engaging responses. In this paper we show that social dialogue systems can be trained effectively from raw unannotated data. Using a dataset of real conversations collected in the 2017 Alexa Prize challenge, we developed a neural ranker1for selecting 'good' system responses to user utterances, i.e. responses which are likely to lead to long and engaging conversations. We show that (1) our neural ranker consistently outperforms several strong baselines when trained to optimise for user ratings;(2) when trained on larger amounts of data and only using conversation length as the objective, the ranker performs better than the one trained using ratings - ultimately reaching a Precision@1 of 0:87. This advance will make data collection for social conversational agents simpler and less expensive in the future. Copyright © 2018, The Authors. All rights reserved.

关键词： Speech processing

Multi-task learning for domain-general spoken disfluency detection in dialogue systems

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Shalyminov, Igor Eshghi, Arash Lemon, Oliver Interaction Lab Department of Computer Science Heriot-Watt University EdinburghEH14 4AS United Kingdom

Spontaneous spoken dialogue is often disfluent, containing pauses, hesitations, self-corrections and false starts. Processing such phenomena is essential in understanding a speaker's intended meaning and controlling the flow of the conversation. Furthermore, this processing needs to be word-by-word incremental to allow further downstream processing to begin as early as possible in order to handle real spontaneous human conversational behaviour. In addition, from a developer's point of view, it is highly desirable to be able to develop systems which can be trained from 'clean' examples while also able to generalise to the very diverse disfluent variations on the same data - thereby enhancing both data-efficiency and robustness. In this paper, we present a multitask LSTM-based model for incremental detection of disfluency structure1, which can be hooked up to any component for incremental interpretation (e.g. an incremental semantic parser), or else simply used to 'clean up' the current utterance as it is being produced. We train the system on the Switchboard Dialogue Acts (SWDA) corpus and present its accuracy on this dataset. Our model outperforms prior neural network-based incremental approaches by about 10 percentage points on SWDA while employing a simpler architecture. To test the model's generalisation potential, we evaluate the same model on the bAbI+ dataset, without any additional training. bAbI+ is a dataset of synthesised goal-oriented dialogues where we control the distribution of disfluencies and their types. This shows that our approach has good generalisation potential, and sheds more light on which types of disfluency might be amenable to domain-general processing. Copyright © 2018, The Authors. All rights reserved.

关键词： Statistical tests

Revisiting Shadow Detection: A New Benchmark Dataset for Complex World

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Hu, Xiaowei Wang, Tianyu Fu, Chi-Wing Jiang, Yitong Wang, Qiong Heng, Pheng-Ann The Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong Shenzhen Key Laboratory of Virtual Reality and Human Interaction Technology Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China

Shadow detection in general photos is a nontrivial problem, due to the complexity of the real world. Though recent shadow detectors have already achieved remarkable performance on various benchmark data, their performance is still limited for general real-world situations. In this work, we collected shadow images for multiple scenarios and compiled a new dataset of 10,500 shadow images, each with labeled ground-truth mask, for supporting shadow detection in the complex world. Our dataset covers a rich variety of scene categories, with diverse shadow sizes, locations, contrasts, and types. Further, we comprehensively analyze the complexity of the dataset, present a fast shadow detection network with a detail enhancement module to harvest shadow details, and demonstrate the effectiveness of our method to detect shadows in general situations. Copyright © 2019, The Authors. All rights reserved.

关键词： Deep neural networks

Ontologizing Health Systems Data at Scale: Making Translational Discovery a Reality

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Callahan, Tiffany J. Stefanski, Adrianne L. Wyrwa, Jordan M. Zeng, Chenjie Ostropolets, Anna Banda, Juan M. Baumgartner, William A. Boyce, Richard D. Casiraghi, Elena Coleman, Ben D. Collins, Janine H. Deakyne-Davies, Sara J. Feinstein, James A. Haendel, Melissa A. Lin, Asiyah Y. Martin, Blake Matentzoglu, Nicolas A. Meeker, Daniella Reese, Justin Sinclair, Jessica Taneja, Sanya B. Trinkley, Katy E. Vasilevsky, Nicole A. Williams, Andrew Zhang, Xingman A. Denny, Joshua C. Robinson, Peter N. Ryan, Patrick Hripcsak, George Bennett, Tellen D. Hunter, Lawrence E. Kahn, Michael G. Computational Bioscience Program University of Colorado Anschutz Medical Campus AuroraCO80045 United States Department of Biomedical Informatics Columbia University Irving Medical Center New YorkNY10032 United States Department of Physical Medicine and Rehabilitation School of Medicine University of Colorado Anschutz Medical Campus AuroraCO80045 United States National Human Genome Research Institute National Institutes of Health BethesdaMD20892 United States Department of Computer Science Georgia State University AtlantaGA30303 United States Department of Biomedical Informatics University of Pittsburgh School of Medicine PittsburghPA15260 United States Computer Science Università degli Studi di Milano Milan20122 Italy Division of Environmental Genomics and Systems Biology Lawrence Berkeley National Laboratory BerkeleyCA94720 United States The Jackson Laboratory for Genomic Medicine FarmingtonCT06032 United States Department of Haematology University of Cambridge Cambridge United Kingdom Department of Research Informatics & Data Science Analytics Resource Center Children’s Hospital Colorado AuroraCO80045 United States University of Colorado Anschutz School of Medicine AuroraCO80045 United States Center for Health AI University of Colorado Anschutz Medical Campus AuroraCO80045 United States Departments of Biomedical Informatics and Pediatrics University of Colorado School of Medicine AuroraCO80045 United States Semanticly Athens Greece Yale School of Medicine New HavenCT06510 United States HealthLinc ValparaisoIN46383 United States Intelligent Systems Program University of Pittsburgh PittsburghPA15260 United States Department of Family Medicine University of Colorado Anschutz School of Medicine AuroraCO80045 United States Translational and Integrative Sciences Lab University of Colorado Anschutz Medical Campus AuroraCO80045 United States Tufts Institute for Clinical Research and Health Policy Studies Tufts University Bos

Background: Common data models solve many challenges of standardizing electronic health record (EHR) data, but are unable to semantically integrate all the resources needed for deep phenotyping. Open Biological and Biomedical Ontology (OBO) Foundry ontologies provide computable representations of biological knowledge and enable the integration of heterogeneous data. However, mapping EHR data to OBO ontologies requires significant manual curation and domain expertise. Objective: We introduce OMOP2OBO, an algorithm for mapping Observational Medical Outcomes Partnership (OMOP) vocabularies to OBO ontologies. Results: Using OMOP2OBO, we produced mappings for 92,367 conditions, 8611 drug ingredients, and 10,673 measurement results, which covered 68-99% of concepts used in clinical practice when examined across 24 hospitals. When used to phenotype rare disease patients, the mappings helped systematically identify undiagnosed patients who might benefit from genetic testing. Conclusions: By aligning OMOP vocabularies to OBO ontologies our algorithm presents new opportunities to advance EHR-based deep phenotyping. © 2022, CC BY.

关键词： Ontology

A knowledge-grounded multimodal search-based conversational agent

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Agarwal, Shubham Dušek, Ondřej Konstas, Ioannis Rieser, Verena Interaction Lab Department of Computer Science Heriot-Watt University Edinburgh United Kingdom Adeptmind Inc. Toronto Canada

Multimodal search-based dialogue is a challenging new task: It extends visually grounded question answering systems into multi-turn conversations with access to an external database. We address this new challenge by learning a neural response generation system from the recently released Multimodal Dialogue (MMD) dataset (Saha et al., 2017). We introduce a knowledge-grounded multimodal conversational model where an encoded knowledge base (KB) representation is appended to the decoder input. Our model substantially outperforms strong baselines in terms of text-based similarity measures (over 9 BLEU points, 3 of which are solely due to the use of additional information from the KB). Copyright © 2018, The Authors. All rights reserved.

关键词： Knowledge based systems

Improving context modelling in multimodal dialogue generation

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Agarwal, Shubham Dušek, Ondřej Konstas, Ioannis Rieser, Verena Interaction Lab Department of Computer Science Heriot-Watt University Edinburgh United Kingdom Adeptmind Inc. Toronto Canada

In this work, we investigate the task of textual response generation in a multimodal task-oriented dialogue system. Our work is based on the recently released Multimodal Dialogue (MMD) dataset (Saha et al., 2017) in the fashion domain. We introduce a multimodal extension to the Hierarchical Recurrent Encoder-Decoder (HRED) model and show that this extension outperforms strong baselines in terms of text-based similarity metrics. We also showcase the shortcomings of current vision and language models by performing an error analysis on our system's output. Copyright © 2018, The Authors. All rights reserved.

关键词： Speech processing

Usability methods for designing programming languages for software engineers

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Coblenz, Michael Kambhatla, Gauri Koronkevich, Paulette Wise, Jenna L. Barnaby, Celeste Sunshine, Joshua Aldrich, Jonathan Myers, Brad A. Carnegie Mellon Unversity Computer Science Department Carnegie Mellon University 5000 Forbes Ave. PittsburghPA15213 United States Computer Science Department University of Michigan 500 S. State St. Ann ArborMI48109 United States Computer Science Department University of British Columbia 2329 West Mall VancouverBCV6T 1Z4 Canada Institute for Software Research Carnegie Mellon University 5000 Forbes Ave. PittsburghPA15213 United States Facebook Inc. 1 Hacker Way Menlo ParkCA94025 United States Human-Computer Interaction Institute Carnegie Mellon University 5000 Forbes Ave. PittsburghPA15213 United States

Programming language design requires making many usability-related design decisions. We explored using user-centered methods to make languages more effective for programmers. However, existing HCI methods expect iteration with appropriate users, who must learn to use the language to be evaluated. These methods were impractical to apply to programming languages: they have high iteration costs, programmers require significant learning time, and user performance has high variance. To address these problems, we adapted HCI methods to reduce iteration and training costs and designed tasks and analyses that mitigated the high variance. We evaluated the methods by using them to design two languages for professional developers. Glacier extends Java to enable programmers to express immutability properties effectively and easily. Obsidian is a language for blockchains that includes verification of critical safety properties. Summative usability studies showed that programmers were able to program effectively in both languages after short training periods. Copyright © 2019, The Authors. All rights reserved.

关键词： Usability engineering