CEUR workshop proceedings最新文献

A Privacy-Preserving Unsupervised Speaker Disentanglement Method for Depression Detection from Speech. 一种用于从语音中检测抑郁的隐私保护无监督扬声器纠错方法

CEUR workshop proceedings Pub Date : 2024-02-01

Vijay Ravi, Jinhan Wang, Jonathan Flint, Abeer Alwan

{"title":"A Privacy-Preserving Unsupervised Speaker Disentanglement Method for Depression Detection from Speech.","authors":"Vijay Ravi, Jinhan Wang, Jonathan Flint, Abeer Alwan","doi":"","DOIUrl":"","url":null,"abstract":"The proposed method focuses on speaker disentanglement in the context of depression detection from speech signals. Previous approaches require patient/speaker labels, encounter instability due to loss maximization, and introduce unnecessary parameters for adversarial domain prediction. In contrast, the proposed unsupervised approach reduces cosine similarity between latent spaces of depression and pre-trained speaker classification models. This method outperforms baseline models, matches or exceeds adversarial methods in performance, and does so without relying on speaker labels or introducing additional model parameters, leading to a reduction in model complexity. The higher the speaker de-identification score (DeID), the better the depression detection system is in masking a patient's identity thereby enhancing the privacy attributes of depression detection systems. On the DAIC-WOZ dataset with ComparE16 features and an LSTM-only model, our method achieves an F1-Score of 0.776 and a DeID score of 92.87%, outperforming its adversarial counterpart which has an F1Score of 0.762 and 68.37% DeID, respectively. Furthermore, we demonstrate that speaker-disentanglement methods are complementary to text-based approaches, and a score-level fusion with a Word2vec-based depression detection model further enhances the overall performance to an F1-Score of 0.830.","PeriodicalId":72554,"journal":{"name":"CEUR workshop proceedings","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11034881/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140875057","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Internet resources for foreign language education in primary school: challenges and opportunities 小学外语教育的网络资源:挑战与机遇

CEUR workshop proceedings Pub Date : 2023-09-12 DOI: 10.55056/ceur-ws.org/vol-3482/paper041

Inna A. Kravtsova, Alina O. Mankuta, Vita A. Hamaniuk, Olga S. Bilozir, Andrei V. Voznyak

引用次数: 0

YouTube as an open resource for foreign language learning: a case study of German YouTube作为外语学习的开放资源:以德语为例

CEUR workshop proceedings Pub Date : 2023-09-12 DOI: 10.55056/ceur-ws.org/vol-3482/paper116

Olha V. Chorna, Vita A. Hamaniuk, Oksana Y. Markheva, Andrei V. Voznyak

{"title":"YouTube as an open resource for foreign language learning: a case study of German","authors":"Olha V. Chorna, Vita A. Hamaniuk, Oksana Y. Markheva, Andrei V. Voznyak","doi":"10.55056/ceur-ws.org/vol-3482/paper116","DOIUrl":"https://doi.org/10.55056/ceur-ws.org/vol-3482/paper116","url":null,"abstract":"The integration of information and communication technologies (ICT) in education has increased the possibilities and expanded the boundaries of the learning process. It is also a prerequisite for implementing distance learning. Various online resources, such as e-mail, blogs, forums, online applications, and video hosting sites, can be used to create open learning and education environments. This study focuses on the use of informational educational technologies for learning foreign languages, especially German. The article presents the results of a theoretical analysis of the content of YouTube video materials in terms of their personal and didactic relevance for teaching German as a first or second foreign language in higher education, specifically at a pedagogical university. Based on the practical experience of using several popular thematic YouTube channels with a large and stable audience, a brief didactic analysis of their products is provided and suggestions are made on how to transform video content into methodological material for the practical course of German language for future teachers. The article also explores the potential of using alternative YouTube resources for distance learning with regard to the development of mediation skills as defined by the authors of the CEFR Companion Volume with New Descriptors. Four types of resources that can serve as teaching materials are identified and analyzed; some examples of their preparation and use for the training of future foreign language teachers are given. The article also discusses the open resources ONCOO and TWINE, which can be used to foster the autonomy of future foreign language teachers, and describes their features. The proposed recommendations can help to achieve the following objectives: enriching vocabulary; semanticizing phraseological units, fixed expressions, clichés; developing pronunciation skills; enhancing linguistic and ICT competencies; improving listening and speaking skills; increasing motivation to learn, etc.","PeriodicalId":72554,"journal":{"name":"CEUR workshop proceedings","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135935773","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Comparison of Human Experts and AI in Predicting Autism from Facial Behavior. 人类专家和人工智能从面部行为预测自闭症的比较。

CEUR workshop proceedings Pub Date : 2023-03-01 Epub Date: 2023-03-16

Evangelos Sariyanidi, Casey J Zampella, Ellis DeJardin, John D Herrington, Robert T Schultz, Birkan Tunc

{"title":"Comparison of Human Experts and AI in Predicting Autism from Facial Behavior.","authors":"Evangelos Sariyanidi, Casey J Zampella, Ellis DeJardin, John D Herrington, Robert T Schultz, Birkan Tunc","doi":"","DOIUrl":"","url":null,"abstract":"Advances in computational behavior analysis via artificial intelligence (AI) promise to improve mental healthcare services by providing clinicians with tools to assist diagnosis or measurement of treatment outcomes. This potential has spurred an increasing number of studies in which automated pipelines predict diagnoses of mental health conditions. However, a fundamental question remains unanswered: How do the predictions of the AI algorithms correspond and compare with the predictions of humans? This is a critical question if AI technology is to be used as an assistive tool, because the utility of an AI algorithm would be negligible if it provides little information beyond what clinicians can readily infer. In this paper, we compare the performance of 19 human raters (8 autism experts and 11 non-experts) and that of an AI algorithm in terms of predicting autism diagnosis from short (3-minute) videos of N = 42 participants in a naturalistic conversation. Results show that the AI algorithm achieves an average accuracy of 80.5%, which is comparable to that of clinicians with expertise in autism (83.1%) and clinical research staff without specialized expertise (78.3%). Critically, diagnoses that were inaccurately predicted by most humans (experts and non-experts, alike) were typically correctly predicted by AI. Our results highlight the potential of AI as an assistive tool that can augment clinician diagnostic decision-making.","PeriodicalId":72554,"journal":{"name":"CEUR workshop proceedings","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10687770/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138464759","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

An Extendible Realism-Based Ontology for Kinship. 基于现实主义的可扩展亲缘关系本体论。

CEUR workshop proceedings Pub Date : 2023-01-01

Michael Rabenberg, Anuwat Pengput, Werner Ceusters

引用次数: 0

Fast Optimization of Weighted Sparse Decision Trees for use in Optimal Treatment Regimes and Optimal Policy Design. 快速优化加权稀疏决策树，用于优化治疗机制和优化政策设计。

CEUR workshop proceedings Pub Date : 2022-10-01

Ali Behrouz, Mathias Lécuyer, Cynthia Rudin, Margo Seltzer

{"title":"Fast Optimization of Weighted Sparse Decision Trees for use in Optimal Treatment Regimes and Optimal Policy Design.","authors":"Ali Behrouz, Mathias Lécuyer, Cynthia Rudin, Margo Seltzer","doi":"","DOIUrl":"","url":null,"abstract":"Sparse decision trees are one of the most common forms of interpretable models. While recent advances have produced algorithms that fully optimize sparse decision trees for prediction, that work does not address policy design, because the algorithms cannot handle weighted data samples. Specifically, they rely on the discreteness of the loss function, which means that real-valued weights cannot be directly used. For example, none of the existing techniques produce policies that incorporate inverse propensity weighting on individual data points. We present three algorithms for efficient sparse weighted decision tree optimization. The first approach directly optimizes the weighted loss function; however, it tends to be computationally inefficient for large datasets. Our second approach, which scales more efficiently, transforms weights to integer values and uses data duplication to transform the weighted decision tree optimization problem into an unweighted (but larger) counterpart. Our third algorithm, which scales to much larger datasets, uses a randomized procedure that samples each data point with a probability proportional to its weight. We present theoretical bounds on the error of the two fast methods and show experimentally that these methods can be two orders of magnitude faster than the direct optimization of the weighted loss, without losing significant accuracy.","PeriodicalId":72554,"journal":{"name":"CEUR workshop proceedings","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10039433/pdf/nihms-1883491.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"9197753","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Fast optimization of weighted sparse decision trees for use in optimal treatment regimes and optimal policy design 加权稀疏决策树的快速优化，用于最优治疗方案和最优策略设计

CEUR workshop proceedings Pub Date : 2022-10-01 DOI: 10.48550/arXiv.2210.06825

Ali Behrouz, Mathias Lécuyer, C. Rudin, M. Seltzer

{"title":"Fast optimization of weighted sparse decision trees for use in optimal treatment regimes and optimal policy design","authors":"Ali Behrouz, Mathias Lécuyer, C. Rudin, M. Seltzer","doi":"10.48550/arXiv.2210.06825","DOIUrl":"https://doi.org/10.48550/arXiv.2210.06825","url":null,"abstract":"Sparse decision trees are one of the most common forms of interpretable models. While recent advances have produced algorithms that fully optimize sparse decision trees for prediction, that work does not address policy design, because the algorithms cannot handle weighted data samples. Specifically, they rely on the discreteness of the loss function, which means that real-valued weights cannot be directly used. For example, none of the existing techniques produce policies that incorporate inverse propensity weighting on individual data points. We present three algorithms for efficient sparse weighted decision tree optimization. The first approach directly optimizes the weighted loss function; however, it tends to be computationally inefficient for large datasets. Our second approach, which scales more efficiently, transforms weights to integer values and uses data duplication to transform the weighted decision tree optimization problem into an unweighted (but larger) counterpart. Our third algorithm, which scales to much larger datasets, uses a randomized procedure that samples each data point with a probability proportional to its weight. We present theoretical bounds on the error of the two fast methods and show experimentally that these methods can be two orders of magnitude faster than the direct optimization of the weighted loss, without losing significant accuracy.","PeriodicalId":72554,"journal":{"name":"CEUR workshop proceedings","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45358116","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2

A community effort for COVID-19 Ontology Harmonization. COVID-19 本体协调的社区努力。

CEUR workshop proceedings Pub Date : 2022-01-01 Epub Date: 2022-01-28

Asiyah Yu Lin, Yuki Yamagata, William D Duncan, Leigh C Carmody, Tatsuya Kushida, Hiroshi Masuya, John Beverley, Biswanath Dutta, Michael DeBellis, Zoë May Pendlington, Paola Roncaglia, Yongqun He

引用次数: 0

An Open-Publishing Response to the COVID-19 Infodemic. 对 COVID-19 信息学术会议的公开出版回应。

CEUR workshop proceedings Pub Date : 2021-09-01

Halie M Rando, Simina M Boca, Lucy D'Agostino McGowan, Daniel S Himmelstein, Michael P Robson, Vincent Rubinetti, Ryan Velazquez, Casey S Greene, Anthony Gitter

{"title":"An Open-Publishing Response to the COVID-19 Infodemic.","authors":"Halie M Rando, Simina M Boca, Lucy D'Agostino McGowan, Daniel S Himmelstein, Michael P Robson, Vincent Rubinetti, Ryan Velazquez, Casey S Greene, Anthony Gitter","doi":"","DOIUrl":"","url":null,"abstract":"The COVID-19 pandemic catalyzed the rapid dissemination of papers and preprints investigating the disease and its associated virus, SARS-CoV-2. The multifaceted nature of COVID-19 demands a multidisciplinary approach, but the urgency of the crisis combined with the need for social distancing measures present unique challenges to collaborative science. We applied a massive online open publishing approach to this problem using Manubot. Through GitHub, collaborators summarized and critiqued COVID-19 literature, creating a review manuscript. Manubot automatically compiled citation information for referenced preprints, journal publications, websites, and clinical trials. Continuous integration workflows retrieved up-to-date data from online sources nightly, regenerating some of the manuscript's figures and statistics. Manubot rendered the manuscript into PDF, HTML, LaTeX, and DOCX outputs, immediately updating the version available online upon the integration of new content. Through this effort, we organized over 50 scientists from a range of backgrounds who evaluated over 1,500 sources and developed seven literature reviews. While many efforts from the computational community have focused on mining COVID-19 literature, our project illustrates the power of open publishing to organize both technical and non-technical scientists to aggregate and disseminate information in response to an evolving crisis.","PeriodicalId":72554,"journal":{"name":"CEUR workshop proceedings","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9093051/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142094263","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Coverage of the Coronavirus Pandemic through Entropy Measures 通过熵测度对冠状病毒大流行的覆盖

CEUR workshop proceedings Pub Date : 2021-03-23 DOI: 10.31812/123456789/4427

V. Soloviev, A. Bielinskyi, N. Kharadzjan

{"title":"Coverage of the Coronavirus Pandemic through Entropy Measures","authors":"V. Soloviev, A. Bielinskyi, N. Kharadzjan","doi":"10.31812/123456789/4427","DOIUrl":"https://doi.org/10.31812/123456789/4427","url":null,"abstract":"The rapidly evolving coronavirus pandemic brings a devastating effect on the entire world and its economy as awhole. Further instability related to COVID-19will negatively affect not only on companies and financial markets, but also on traders and investors that have been interested in saving their investment, minimizing risks, and making decisions such as how to manage their resources, how much to consume and save, when to buy or sell stocks, etc., and these decisions depend on the expectation of when to expect next critical change. Trying to help people in their subsequent decisions, we demonstrate the possibility of constructing indicators of critical and crash phenomena on the example of Bitcoin market crashes for further demonstration of their efficiency on the crash that is related to the coronavirus pandemic. For this purpose, the methods of the theory of complex systems have been used. Since the theory of complex systems has quite an extensive toolkit for exploring the nonlinear complex system, we take a look at the application of the concept of entropy in finance and use this concept to construct 6 effective entropy measures: Shannon entropy, Approximate entropy, Permutation entropy, and 3 Recurrence based entropies. We provide computational results that prove that these indicators could have been used to identify the beginning of the crash and predict the future course of events associated with the current pandemic.","PeriodicalId":72554,"journal":{"name":"CEUR workshop proceedings","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-03-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79338041","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 14