检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Wang, Xiaonan Yeo, Jinyoung Lim, Joon-Ho Kim, Hansaem Interdisciplinary Graduate Program of Linguistics and Informatics Yonsei University Korea Republic of Department of Artificial Intelligence Yonsei University Korea Republic of Tutorus Labs Korea Republic of

Large language models (LLMs) have exhibited significant enhancements in performance across various tasks. However, the complexity of their evaluation increases as these models generate more fluent and coherent content. Current multilingual benchmarks often use translated English versions, which may incorporate Western cultural biases that do not accurately assess other languages and cultures. To address this research gap, we introduce KULTURE Bench, an evaluation framework specifically designed for Korean culture that features datasets of cultural news, idioms, and poetry. It is designed to assess language models' cultural comprehension and reasoning capabilities at the word, sentence, and paragraph levels. Using the KULTURE Bench, we assessed the capabilities of models trained with different language corpora and analyzed the results comprehensively. The results show that there is still significant room for improvement in the models' understanding of texts related to the deeper aspects of Korean culture. Copyright © 2024, The Authors. All rights reserved.

关键词： Translation (languages)

来源：评论

学校读者我要写书评

暂无评论

SwiftMedSAM: An Ultra-lightweight Prompt-Based Universal Medical Image Segmentation Model for Highly Constrained Environments 1

引用

International Challenge on Segment Anything in Medical Images on Laptop held in conjunction with the IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2024

作者： Kong, Youngbin Kim, Kwangtai Jeong, Seoi Lee, Kyu Eun Kong, Hyoun-Joong Interdisciplinary Program in Bioengineering Graduate School Seoul National University Seoul Korea Republic of Department of Transdisciplinary Medicine Seoul National University Hospital Seoul Korea Republic of Department of Surgery Seoul National University Hospital and College of Medicine Seoul Korea Republic of Department of Medicine Seoul National University College of Medicine Seoul Korea Republic of Innovative Medical Technology Research Institute Seoul National University Hospital Seoul Korea Republic of Interdisciplinary Program of Medical Informatics Seoul National University College of Medicine Seoul Korea Republic of

ISBN: (数字)9783031818547

ISBN: (纸本)9783031818530

Medical image segmentation is a crucial step for accurate diagnosis and treatment planning, as it provides quantitative information about anatomical structures and pathological lesions in various clinical scenarios. However, the existing methodologies have limitations in terms of their generalizability and computational efficiency. In this study, we propose SwiftMedSAM, an ultra-lightweight prompt-based general model, to enable efficient medical image segmentation even in resource-constrained environments. Based on LiteMedSAM, we significantly reduced the model size and computational complexity through the hyperparameter optimization of the image encoder and mask decoder components. SwiftMedSAM showed remarkable performance across various imaging modalities enabling real-time inference in resource-limited computing environments. It achieved a validation score of 0.75 demonstrating that SwiftMedSAM outperformed the existing methodologies in terms of the trade-off between accuracy and efficiency. Owing to its unprecedented generalizability and low computational cost, SwiftMedSAM is expected to enable high-quality medical image analysis in resource-constrained settings, thereby contributing to advancements in precision medicine and telemedicine. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

Multiclass Classification of Online Comments Based on Toxicity Scale 14th

Multiclass Classification of Online Comments Based on Toxici...

引用

14th International Conference on Computer Science and its Applications, CSA 2022 and the 16th KIPS International Conference on Ubiquitous Information Technologies and Applications, CUTE 2022

作者： eun Kang, Jo Kim, Jisun su Do, Hyeon Oh, Sihyun hwa Lee, Si jee Jeung, Min seo Choi, Min Oh, Se Jong Doo, Ill Chul Department of Interdisciplinary Graduate Program of Linguistics and Informatics Yonsei University Graduate School Seoul Korea Republic of Department of Political Science and International Relations Hankuk University of Foreign Studies Seoul Korea Republic of Department of Japanese Language and Culture Soochow University Taipei Taiwan Department of English Linguistics & Language Technology Hankuk University of Foreign Studies Seoul Korea Republic of Department of Hungarian Hankuk University of Foreign Studies Yongin Korea Republic of Department of French Studies Hankuk University of Foreign Studies Yongin Korea Republic of Department of Information Communications Engineering Hankuk University of Foreign Studies Yongin Korea Republic of Artificial Intelligence Education Hankuk University of Foreign Studies Yongin Korea Republic of

ISBN: (纸本)9789819912513

Our research specifies the criteria for categorizing comments and supplements the limitations of the existing services that filter out only some of the direct malicious comments centered on specific vocabulary and phrases. In comparison to prior research detecting three sentiments as positive, negative, or neutral, we subdivided expressions into six categories. Our model applying classification downstream tasks to a pre-trained KcBERT model draws results reflecting the meaning and social context of the comments. An improved accuracy compared to previous studies shows a meaningful outcome. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Neural correlates of understanding emotional words in late childhood

引用

International Journal of Psychophysiology 2023年第0期183卷 19-31页

作者： Yeh, Pei-Wen Lee, Chia-Ying Cheng, Ying-Ying Chiang, Chung-Hsin Department of Psychology Kaohsiung Medical University Institute of Linguistics Academia Sinica Laboratory of Brain and Language Taipei Taiwan Department of Psychology National Chengchi University Taipei Taiwan Research Center for Mind Brain and Learning National Chengchi University Taipei Taiwan Institute of Cognitive Neuroscience National Central University Taoyuan Taiwan Interdisciplinary Neuroscience Taiwan International Graduate Program Academia Sinica Taipei Taiwan

Prior studies involving adults have shown that words can elicit emotional processing, with emotion-label (e.g., happiness) and emotion-laden words (e.g., gift) having distinct processes. However, limited studies have explored the developmental changes in these processes in relation to emotional valence. To address this question, this exploratory study measured event-related potentials (ERPs) in 11–14-year-old children/adolescents (N = 25) and adults (N = 23) while performing an emotional categorization task. The stimuli used were two-character Chinese words, with factors for word type (emotion-label versus emotion-laden) and valence (positive versus negative). To confirm word emotionality, neutral words were also included and compared with all emotional words. The results showed that adults exhibited reduced N400 amplitudes to emotion-label words compared to emotion-laden ones in both positive and negative valence contexts. The differentiation was only sustained for negative valence in the late positive component (LPC). Similar scalp distributions of the effects of word type were found in children/adolescents;however, they exhibited a more prolonged processing of all emotional words than adults. These results suggest that the processing of emotion-label and emotion-laden words are distinct in late childhood, and this discrepancy varies with emotional valence and increasing age. © 2022 Elsevier B.V.

关键词： Emotion Emotion-label words Emotion-laden words Event-related potentials (ERPs) Late positive complex(LPC) N400

来源：评论

学校读者我要写书评

暂无评论

Dynamic Healthcare Embeddings for Improving Patient Care 14

Dynamic Healthcare Embeddings for Improving Patient Care

引用

14th IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2022

作者： Jang, Hankyu Lee, Sulyun Hasibul Hasan, D.M. Polgreen, Philip M. Pemmaraju, Sriram V. Adhikari, Bijaya University of Iowa Department of Computer Science Iowa CityIA United States University of Iowa Interdisciplinary Graduate Program in Informatics Iowa CityIA United States University of Iowa Department of Internal Medicine Iowa CityIA United States

ISBN: (纸本)9781665456616

As hospitals move towards automating and integrating their computing systems, more fine-grained hospital operations data are becoming available. These data include hospital architectural drawings, logs of interactions between patients and healthcare professionals, prescription data, procedures data, and data on patient admission, discharge, and transfers. This has opened up many fascinating avenues for healthcare-related prediction tasks for improving patient care. However, in order to leverage off-the-shelf machine learning software for these tasks, one needs to learn structured representations of entities involved from heterogeneous, dynamic data streams. Here, we propose DECENT, an auto-encoding heterogeneous co-evolving dynamic neural network, for learning heterogeneous dynamic embeddings of patients, doctors, rooms, and medications from diverse data streams. These embeddings capture similarities among doctors, rooms, patients, and medications based on static attributes and dynamic interactions. DECENT enables several applications in healthcare prediction, such as predicting mortality risk and case severity of patients, adverse events (e.g., transfer back into an intensive care unit), and future healthcare-associated infections. The results of using the learned patient embeddings in predictive modeling show that DECENT has a gain of up to 48.1% on the mortality risk prediction task, 12.6% on the case severity prediction task, 6.4% on the medical intensive care unit transfer task, and 3.8% on the Clostridioides difficile (***) Infection (CDI) prediction task over the state-of-the-art baselines. In addition, case studies on the learned doctor, medication, and room embeddings show that our approach learns meaningful and interpretable embeddings. © 2022 IEEE.

关键词： Heterogeneous networks

来源：评论

学校读者我要写书评

暂无评论

Learners' bias to balance production effort against message uncertainty is independent of their native language 42

Learners' bias to balance production effort against message ...

引用

42nd Annual Meeting of the Cognitive Science Society: Developing a Mind: Learning in Humans, Animals, and Machines, CogSci 2020

作者： Hartley, Lucy Hall Fedzechkina, Masha Department of Linguistics University of Arizona TucsonAZ85719 United States Department of Linguistics Graduate Interdisciplinary Program in Cognitive Science Graduate Interdisciplinary Program in Second Language Acquisition and Teaching University of Arizona TucsonAZ85719 United States

Miniature language learning is gaining increasing popularity to study biases underlying language universals. However, it is unclear whether learning preferences in these studies are influenced by learners' native language. We ask whether a previously identified bias to balance production effort against message uncertainty holds across speakers of structurally different languages. We expose English (fixed order language without case) and German (flexible order language with case) speakers to miniature languages with optional case and either fixed or flexible constituent order and study their deviations from the input. We find that English and German speakers restructure the input in the same way: They match the input constituent order proportions and use more case in the flexible order language than in the fixed order language, thus following the bias to balance production effort against message uncertainty. Our findings suggest that this bias and its specific realization are independent of learners' native language. © 2020 The Author(s). This work is licensed under a Creative Commons Attribution 4.0 International License (CC BY)

关键词： efficient information transmission L1 influences language evolution Language universals miniature language learning

来源：评论

学校读者我要写书评

暂无评论

Dynamic Healthcare Embeddings for Improving Patient Care

arXiv

引用

arXiv 2023年

作者： Jang, Hankyu Lee, Sulyun Hasan, D.M. Hasibul Polgreen, Philip M. Pemmaraju, Sriram V. Adhikari, Bijaya Department of Computer Science University of Iowa Iowa CityIA United States Interdisciplinary Graduate Program in Informatics University of Iowa Iowa CityIA United States CDC MInD Healthcare Network United States

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Learners sacrifice robust communication as a result of a social bias 42

Learners sacrifice robust communication as a result of a soc...

引用

42nd Annual Meeting of the Cognitive Science Society: Developing a Mind: Learning in Humans, Animals, and Machines, CogSci 2020

作者： Fedzechkina, Masha Roberts, Gareth Department of Linguistics Graduate Interdisciplinary Program in Cognitive Science Graduate Interdisciplinary Program in Second Language Acquisition and Teaching University of Arizona P.O. Box 210025 TucsonAZ85719 United States Department of Linguistics University of Pennsylvania 3401 Walnut Street PhiladelphiaPA19147 United States

Languages are subject to many competing pressures, which originate in individual-level learning and communication biases and in social biases reflecting community-level dynamics. Recent work suggests that certain aspects of language structure, such as the cross-linguistic trade-off between case and constituent-order flexibility, originate in learners' biases for efficient communication: Learners drop redundant case but retain informative case in production. Social biases can lead to retention of redundant case, resulting in systems that require more effort to produce. It is not clear, however, whether social biases can influence the use of informative cues. We tested this by exposing participants to a language with uninformative constituent order and two dialects, only one of which employed case. We manipulated the presence of social biases for and against the case dialect. Learners biased towards the no-case dialect dropped informative case without compensating for the resulting message uncertainty. Case was retained in all other conditions. © 2020 The Author(s). This work is licensed under a Creative Commons Attribution 4.0 International License (CC BY)

关键词： Economic and social effects

来源：评论

学校读者我要写书评

暂无评论

D-SRGAN: DEM Super-Resolution with Generative Adversarial Networks

引用

SN Computer Science 2021年第1期2卷 48页

作者： Demiray, Bekir Z. Sit, Muhammed Demir, Ibrahim Department of Computer Science University of Iowa Iowa City United States Interdisciplinary Graduate Program in Informatics University of Iowa Iowa City United States Department of Civil and Environmental Engineering University of Iowa Iowa City United States Department of Electrical and Computer Engineering University of Iowa Iowa City United States

Digital elevation model (DEM) is a critical data source for variety of applications such as road extraction, hydrological modeling, flood mapping, and many geospatial studies. The usage of high-resolution DEMs as inputs in many application areas improves the overall reliability and accuracy of the raw dataset. The goal of this study is to develop a machine learning model that increases the spatial resolution of DEM without additional information. In this paper, a GAN based model (D-SRGAN), inspired by single image super-resolution methods, is developed and evaluated to increase the resolution of DEMs. The experiment results show that D-SRGAN produces promising results while constructing 3 feet high-resolution DEMs from 50 feet low-resolution DEMs. It outperforms common statistical interpolation methods and neural network *** study shows that it is possible to use the power of artificial neural networks to increase the resolution of the DEMs. The study also demonstrates that approaches from single image super-resolution can be applied for DEM super-resolution. © 2021, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. part of Springer Nature.

关键词： Deep learning DEM DEM reconstruction Generative adversarial networks (GANs) Super-resolution

来源：评论

学校读者我要写书评

暂无评论

Dynamic Healthcare Embeddings for Improving Patient Care

Dynamic Healthcare Embeddings for Improving Patient Care

引用

International Conference on Advances in Social Network Analysis and Mining, ASONAM

作者： Hankyu Jang Sulyun Lee D. M. Hasibul Hasan Philip M. Polgreen Sriram V. Pemmaraju Bijaya Adhikari Department of Computer Science University of Iowa Iowa City Iowa USA Interdisciplinary Graduate Program in Informatics University of Iowa Iowa City Iowa USA Department of Internal Medicine University of Iowa Iowa City Iowa USA

关键词： Hospitals Social networking (online) Neural networks Machine learning Predictive models Back Software

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：