检索结果-内蒙古大学图书馆

Conference on Empirical Methods in Natural language processing, EMNLP 2015

作者： Gormley, Matthew R. Mo, Yu Dredze, Mark Hurnan Language Technology Center of Excellence Center for Language and Speech Processing Johns Hopkins University BaltimoreMD21218 United States Machine Intelligence and Translation Lab Harbin Institute of Technology Harbin China

ISBN: (纸本)9781941643327

Compositional embedding models build a representation (or embedding) for a linguistic structure based on its component word embeddings. We propose a Feature-rich Compositional Embedding Model (fcm) for relation extraction that is expressive, generalizes to new domains, and is easy-to-implement. The key idea is to combine both (unlexicalized) handcrafted features with learned word embeddings. The model is able to directly tackle the difficulties met by traditional compositional embeddings models, such as handling arbitrary types of sentence annotations and utilizing global information for composition. We test the proposed model on two relation extraction tasks, and demonstrate that our model outperforms both previous compositional models and traditional feature rich models on the ACE 2005 relation extraction task, and the SemEval 2010 relation classification task. The combination of our model and a loglinear classifier with hand-crafted features gives state-of-the-art results. We made our implementation available for general use1. © 2015 Association for Computational Linguistics.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Content-based recommender systems for spoken documents 40

Content-based recommender systems for spoken documents

引用

40th IEEE International Conference on Acoustics, speech, and Signal processing, ICASSP 2015

作者： Wintrode, Jonathan Sell, Gregory Jansen, Aren Fox, Michelle Garcia-Romero, Daniel McCree, Alan Center for Language and Speech Processing Johns Hopkins University BaltimoreMD United States Human Language Technology Center of Excellence Johns Hopkins University BaltimoreMD United States US Department of Defense WashingtonDC United States

ISBN: (纸本)9781467369978

Content-based recommender systems use preference ratings and features that characterize media to model users' interests or information needs for making future recommendations. While previously developed in the music and text domains, we present an initial exploration of content-based recommendation for spoken documents using a corpus of public domain internet audio. Unlike familiar speech technologies of topic identification and spoken document retrieval, our recommendation task requires a more comprehensive notion of document relevance than bags-of-words would supply. Inspired by music recommender systems, we automatically extract a wide variety of content-based features to characterize non-linguistic aspects of the audio such as speaker, language, gender, and environment. To combine these heterogeneous information sources into a single relevance judgement, we evaluate feature, score, and hybrid fusion techniques. Our study provides an essential first exploration of the task and clearly demonstrates the value of a multisource approach over a bag-of-words baseline. © 2015 IEEE.

关键词： Content-based recommendation i-vectors low resource speech retrieval

来源：评论

学校读者我要写书评

暂无评论

Topic identification and discovery on text and speech

Topic identification and discovery on text and speech

引用

Conference on Empirical Methods in Natural language processing, EMNLP 2015

作者： May, Chandler Ferraro, Francis McCree, Alan Wintrode, Jonathan Garcia-Romero, Daniel Van Durme, Benjamin Human Language Technology Center of Excellence Johns Hopkins University United States

ISBN: (纸本)9781941643327

We compare the multinomial i-vector framework from the speech community with LDA, SAGE, and LSA as feature learners for topic ID on multinomial speech and text data. We also compare the learned representations in their ability to discover topics, quantified by distributional similarity to gold-standard topics and by human interpretability. We find that topic ID and topic discovery are competing objectives. We argue that LSA and i-vectors should be more widely considered by the text processing community as pre-processing steps for downstream tasks, and also speculate about speech processing tasks that could benefit from more interpretable representations like SAGE. © 2015 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

A Domain Independent Approach to Clinical Decision Support 24

A Domain Independent Approach to Clinical Decision Support

引用

24th Text REtrieval Conference, TREC 2015

作者： McNamee, Paul Johns Hopkins University Human Language Technology Center of Excellence United States

Continuing our work from the inaugural running of the Clinical Decision Support track in 2014, we submitted runs to the 2015 evaluation. Our approach this year was very similar to that used in 2014 (Xu et al., 2014). Our submitted runs were created using the JHU HAIRCUT retrieval engine, and featured use of character n-gram indexing and use of pseudo-relevance feedback. The main contribution is investigating the retrieval of scientific medical documents using a domain independent approach. © 2015 24th Text REtrieval Conference, TREC 2015 - Proceedings. All Rights Reserved.

关键词： Decision support systems

来源：评论

学校读者我要写书评

暂无评论

A Framework for Evaluating speech Representations 38

A Framework for Evaluating Speech Representations

引用

38th Annual Meeting of the Cognitive Science Society: Recognizing and Representing Events, CogSci 2016

作者： Richter, Caitlin Feldman, Naomi H. Salgado, Harini Jansen, Aren Department of Linguistics University of Pennsylvania PhiladelphiaPA19104 United States Department of Linguistics UMIACS University of Maryland College ParkMD20742 United States Pomona College ClaremontCA91711 United States Human Language Technology Center of Excellence Johns Hopkins University BaltimoreMD21211 United States

ISBN: (纸本)9780991196739

Listeners track distributions of speech sounds along perceptual dimensions. We introduce a method for evaluating hypotheses about what those dimensions are, using a cognitive model whose prior distribution is estimated directly from speech recordings. We use this method to evaluate two speaker normalization algorithms against human data. Simulations show that representations that are normalized across speakers predict human discrimination data better than unnormalized representations, consistent with previous research. Results further reveal differences across normalization methods in how well each predicts human data. This work provides a framework for evaluating hypothesized representations of speech and lays the groundwork for testing models of speech perception on natural speech recordings from ecologically valid settings. © 2016 Proceedings of the 38th Annual Meeting of the Cognitive Science Society, CogSci 2016. All rights reserved.

关键词： Bayesian networks

来源：评论

学校读者我要写书评

暂无评论

Subnational mapping of HIV incidence and mortality among individuals aged 15–49 years in sub-Saharan Africa, 2000–18: a modelling study

引用

The Lancet HIV 2021年第6期8卷 e363-e375页

作者： Sartorius, Benn VanderHeide, John D. Yang, Mingyou Goosmann, Erik A. Hon, Julia Haeuser, Emily Cork, Michael A. Perkins, Samantha Jahagirdar, Deepa Schaeffer, Lauren E. Serfes, Audrey L. LeGrand, Kate E. Abbastabar, Hedayat Abebo, Zeleke Hailemariam Abosetugn, Akine Eshete Abu-Gharbieh, Eman Accrombessi, Manfred Mario Kokou Adebayo, Oladimeji M. Adegbosin, Adeyinka Emmanuel Adekanmbi, Victor Adetokunboh, Olatunji O. Adeyinka, Daniel Adedayo Ahinkorah, Bright Opoku Ahmadi, Keivan Ahmed, Muktar Beshir Akalu, Yonas Akinyemi, Oluwaseun Oladapo Akinyemi, Rufus Olusola Aklilu, Addis Akunna, Chisom Joyqueenet Alahdab, Fares Al-Aly, Ziyad Alam, Noore Alamneh, Alehegn Aderaw Alanzi, Turki M. Alemu, Biresaw Wassihun Alhassan, Robert Kaba Ali, Tilahun Alipour, Vahid Amini, Saeed Ancuceanu, Robert Ansari, Fereshteh Anteneh, Zelalem Alamrew Anvari, Davood Anwer, Razique Appiah, Seth Christopher Yaw Arabloo, Jalal Asemahagn, Mulusew A. Asghari Jafarabadi, Mohammad Asmare, Wondwossen Niguse Atnafu, Desta Debalkie Atout, Maha Moh'd Wahbi Atreya, Alok Ausloos, Marcel Awedew, Atalel Fentahun Ayala Quintanilla, Beatriz Paulina Ayanore, Martin Amogre Aynalem, Yared Asmare Ayza, Muluken Altaye Azari, Samad Azene, Zelalem Nigussie Babar, Zaheer-Ud-Din Baig, Atif Amin Balakrishnan, Senthilkumar Banach, Maciej Bärnighausen, Till Winfried Basu, Sanjay Bayati, Mohsen Bedi, Neeraj Bekuma, Tariku Tesfaye Bezabhe, Woldesellassie M. Mequanint Bhagavathula, Akshaya Srikanth Bhardwaj, Pankaj Bhattacharyya, Krittika Bhutta, Zulfiqar A. Bibi, Sadia Bikbov, Boris Birhan, Tsegaye Adane Bitew, Zebenay Workneh Bockarie, Moses John Boloor, Archith Brady, Oliver J. Bragazzi, Nicola Luigi Briko, Andrey Nikolaevich Briko, Nikolay Ivanovich Burugina Nagaraja, Sharath Butt, Zahid A. Cárdenas, Rosario Carvalho, Felix Charan, Jaykaran Chatterjee, Souranshu Chattu, Soosanna Kumary Chattu, Vijay Kumar Chowdhury, Mohiuddin Ahsanul Kabir Chu, Dinh-Toi Cook, Aubrey J. Cormier, Natalie Maria Cowden, Richard G. Culquichicon, Carlos Dagnew, Baye Dahlawi, Saad M.A. D Centre for Tropical Medicine and Global Health Nuffield Department of Medicine University of Oxford Oxford United Kingdom Malaria Atlas Project University of Oxford Oxford United Kingdom The George Institute for Global Health University of Oxford Oxford United Kingdom Department of Health Metrics Sciences School of Medicine University of Washington Seattle WA United States Institute for Health Metrics and Evaluation University of Washington Seattle WA United States Department of Global Health University of Washington Seattle WA United States Department of Medicine University of Washington Seattle WA United States Insights Program Bill and Melinda Gates Foundation Seattle WA United States Global Programs Medical Teams International Seattle WA United States Department of Pediatric Newborn Medicine Brigham and Women's Hospital Boston MA United States Advanced Diagnostic and Interventional Radiology Research Center Tehran University of Medical Sciences Tehran Iran Multiple Sclerosis Research Center Tehran University of Medical Sciences Tehran Iran Department of Epidemiology and Biostatistics Tehran University of Medical Sciences Tehran Iran Pediatric Chronic Kidney Disease Research Center Tehran University of Medical Sciences Tehran Iran Department of Environmental Health Engineering Tehran University of Medical Sciences Tehran Iran Metabolomics and Genomics Research Center Tehran University of Medical Sciences Tehran Iran Research Center for Immunodeficiencies Tehran University of Medical Sciences Tehran Iran Department of Public Health Arba Minch University Arba Minch Ethiopia Department of Medical Laboratory Sciences Arba Minch University Arba Minch Ethiopia College of Medicine and Health Science Arba Minch University Arba Minch Ethiopia Department of Nursing Arba Minch University Arba Minch Ethiopia Department of Biomedical Sciences Arba Minch University Arba Minch Ethiopia Department of Public Health Debre Berhan University Debre Brehan

Background: High-resolution estimates of HIV burden across space and time provide an important tool for tracking and monitoring the progress of prevention and control efforts and assist with improving the precision and efficiency of targeting efforts. We aimed to assess HIV incidence and HIV mortality for all second-level administrative units across sub-Saharan Africa. Methods: In this modelling study, we developed a framework that used the geographically specific HIV prevalence data collected in seroprevalence surveys and antenatal care clinics to train a model that estimates HIV incidence and mortality among individuals aged 15–49 years. We used a model-based geostatistical framework to estimate HIV prevalence at the second administrative level in 44 countries in sub-Saharan Africa for 2000–18 and sought data on the number of individuals on antiretroviral therapy (ART) by second-level administrative unit. We then modified the Estimation and Projection Package (EPP) to use these HIV prevalence and treatment estimates to estimate HIV incidence and mortality by second-level administrative unit. Findings: The estimates suggest substantial variation in HIV incidence and mortality rates both between and within countries in sub-Saharan Africa, with 15 countries having a ten-times or greater difference in estimated HIV incidence between the second-level administrative units with the lowest and highest estimated incidence levels. Across all 44 countries in 2018, HIV incidence ranged from 2·8 (95% uncertainty interval 2·1–3·8) in Mauritania to 1585·9 (1369·4–1824·8) cases per 100 000 people in Lesotho and HIV mortality ranged from 0·8 (0·7–0·9) in Mauritania to 676·5 (513·6–888·0) deaths per 100 000 people in Lesotho. Variation in both incidence and mortality was substantially greater at the subnational level than at the national level and the highest estimated rates were accordingly higher. Among second-level administrative units, Guijá District, Gaza Province, Mozambique,

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Limit Theorem for Scaled Eigenvectors of Random Dot Product Graphs

引用

Sankhya A 2016年第1期78卷 1-18页

作者： Athreya, A. Priebe, C.E. Tang, M. Lyzinski, V. Marchette, D.J. Sussman, D.L. Department of Applied Mathematics and Statistics Johns Hopkins University 3400 N. Charles Street Baltimore 21218 MD United States Human Language Technology Center of Excellence Johns Hopkins University Stieff Building 810 Wyman Park Drive Baltimore 21211 MD United States Naval Surface Warfare Center 17320 Dahlgren Road Dahlgren 22448 VA United States Department of Statistics Harvard University Science Center Floor 7 One Oxford St Cambridge 02138 MA United States

We prove a central limit theorem for the components of the largest eigenvectors of the adjacency matrix of a finite-dimensional random dot product graph whose true latent positions are unknown. We use the spectral embedding of the adjacency matrix to construct consistent estimates for the latent positions, and we show that the appropriately scaled differences between the estimated and true latent positions converge to a mixture of Gaussian random variables. We state several corollaries, including an alternate proof of a central limit theorem for the first eigenvector of the adjacency matrix of an Erdos-Rényi random graph. © 2015, Indian Statistical Institute.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Diarization resegmentation in the factor analysis subspace 40

Diarization resegmentation in the factor analysis subspace

引用

40th IEEE International Conference on Acoustics, speech, and Signal processing, ICASSP 2015

作者： Sell, Gregory Garcia-Romero, Daniel Human Language Technology Center of Excellence Johns Hopkins University BaltimoreMD United States

ISBN: (纸本)9781467369978

Resegmentation is an important post-processing step to refine the rough boundaries of diarization systems that rely on segment clustering of an initial uniform segmentation. Past work has primarily used a Viterbi resegmentation with MFCC features for this purpose. In this paper, we examine an algorithm for resegmentation that operates instead in factor analysis subspace. By combining this system with a speaker clustering front-end, we yield a diarization error rate of 11.5% on the CALLHOME conversational telephone speech corpus. © 2015 IEEE.

关键词： factor analysis Speaker diarization variational Bayes

来源：评论

学校读者我要写书评

暂无评论

A concrete Chinese NLP pipeline 14

A concrete Chinese NLP pipeline

引用

14th Conference of the North American Chapter of the Association for Computational Linguistics: human language Technologies, NAACL-HLT 2015

作者： Peng, Nanyun Ferraro, Francis Yu, Mo Andrews, Nicholas DeYoung, Jay Thomas, Max Gormley, Matthew R. Wolfe, Travis Harman, Craig van Durme, Benjamin Dredze, Mark Human Language Technology Center of Excellence Johns Hopkins University BaltimoreMD United States

Natural language processing research increasingly relies on the output of a variety of syntactic and semantic analytics. Yet integrating output from multiple analytics into a single framework can be time consuming and slow research progress. We present a CONCRETE Chinese NLP Pipeline: an NLP stack built using a series of open source systems integrated based on the CONCRETE data schema. Our pipeline includes data ingest, word segmentation, part of speech tagging, parsing, named entity recognition, relation extraction and cross document coreference resolution. Additionally, we integrate a tool for visualizing these annotations as well as allowing for the manual annotation of new data. We release our pipeline to the research community to facilitate work on Chinese language tasks that require rich linguistic annotations. © 2015 NAACL-HLT 2015 - 2015 Conference of the North American Chapter of the Association for Computational Linguistics: human language Technologies - Demonstrations, Proceedings. All Rights Reserved.

关键词： Pipelines

来源：评论

学校读者我要写书评

暂无评论

Entity linking for spoken language

Entity linking for spoken language

引用

Conference of the North American Chapter of the Association for Computational Linguistics: human language Technologies, NAACL HLT 2015

作者： Benton, Adrian Dredze, Mark Human Language Technology Center of Excellence Johns Hopkins University BaltimoreMD United States

ISBN: (纸本)9781941643495

Research on entity linking has considered a broad range of text, including newswire, blogs and web documents in multiple languages. However, the problem of entity linking for spoken language remains unexplored. Spoken language obtained from automatic speech recognition systems poses different types of challenges for entity linking;transcription errors can distort the context, and named entities tend to have high error rates. We propose features to mitigate these errors and evaluate the impact of ASR errors on entity linking using a new corpus of entity linked broadcast news transcripts. © 2015 Association for Computational Linguistics.

关键词： Errors

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：