检索结果-内蒙古大学图书馆

Visual Grounding Helps Learn Word Meanings in Low-Data Regimes

Visual Grounding Helps Learn Word Meanings in Low-Data Regim...

2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL 2024

作者： Zhuang, Chengxu Fedorenko, Evelina Andreas, Jacob McGovern Institute for Brain Research MIT United States Department of Brain and Cognitive Sciences MIT United States The Program in Speech and Hearing Bioscience and Technology Harvard University United States Computer Science and Artificial Intelligence Laboratory MIT United States

ISBN: (纸本)9798891761148

Modern neural language models (LMs) are powerful tools for modeling human sentence production and comprehension, and their internal representations are remarkably well-aligned with representations of language in the human brain. But to achieve these results, LMs must be trained in distinctly un-human-like ways-requiring orders of magnitude more language data than children receive during development, and without perceptual or social context. Do models trained more naturalistically-with grounded supervision-exhibit more human-like language learning? We investigate this question in the context of word learning, a key sub-task in language acquisition. We train a diverse set of LM architectures, with and without auxiliary visual supervision, on datasets of varying scales. We then evaluate these models’ learning of syntactic categories, lexical relations, semantic features, word similarity, and alignment with human neural representations. We find that visual supervision can indeed improve the efficiency of word learning. However, these improvements are limited: they are present almost exclusively in the low-data regime, and sometimes canceled out by the inclusion of rich distributional signals from text. The information conveyed by text and images is not redundant-models mainly driven by visual information yield qualitatively different from those mainly driven by word co-occurrences. However, our results suggest that current multimodal modeling approaches fail to effectively leverage visual information to build human-like word representations from human-scale data. © 2024 Association for Computational Linguistics.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Style Change Detection using Discourse Markers

Style Change Detection using Discourse Markers

引用

2022 Conference and Labs of the Evaluation Forum, CLEF 2022

作者： Alvi, Faisal Algafri, Hasan Alqahtani, Naif Information & Computer Science Department King Fahd University of Petroleum and Minerals Dhahran Saudi Arabia Computer Science Program Dhanani School of Science and Engineering Habib University Karachi Pakistan

This article presents our approach for the Style Change Detection Task at PAN 2022 using discourse markers. Discourse markers (such as ‘what’, ‘I have’, etc.) are words or expressions used to connect, organise and manage conversations. We present two different approaches for Style Change Detection at PAN-2022. For Task 1, (Style Change Basic) our approach is based on identifying conversational patterns within the documents between a user and a possible respondent. Then, using classification algorithms, we predict the point of style change detection within each document. For Task 2 (Style Change Advanced) and Task 3 (Style Change Real World), we use an extensive list of frequently occurring discourse markers to identify the number of speakers as the number of authors within the document. This prediction serves as the number of clusters for text segments within the document. Subsequently, using unsupervised clustering we detect clusters of similar text segments such that each cluster comprises of text segment groups corresponding to each author. The resulting F1 scores for our approaches on the test set are: 0.70518 for Task 1, 0.32128 for Task 2 and 0.56360 for Task 3. © 2022 Copyright for this paper by its authors.

关键词： Change detection

来源：评论

学校读者我要写书评

暂无评论

A Pilot Study on Clinician-AI Collaboration in Diagnosing Depression From Speech

A Pilot Study on Clinician-AI Collaboration in Diagnosing De...

引用

IEEE EMBS International Conference on Information Technology Applications in Biomedicine (ITAB)

作者： Kexin Feng Theodora Chaspari Department of Computer Science and Engineering Texas A&M University College Station Texas USA Department of Computer Science Institute of Cognitive Science University of Colorado Boulder Boulder Colorado USA

ISBN: (数字)9798350351552

ISBN: (纸本)9798350351569

This study investigates clinicians' perceptions and attitudes toward an assistive artificial intelligence (AI) system that employs a speech-based explainable ML algorithm for detecting depression. The AI system detects depression from vowel-based spectrotemporal variations of speech and generates explanations through explainable AI (XAI) methods. It further provides decisions and explanations at various temporal granularities, including utterance groups, individual utterances, and within each utterance. A small-scale user study was conducted to evaluate users' perceived usability of the system, trust in the system, and perceptions of design factors associated with several elements of the system. Quantitative and qualitative analysis of the collected data indicates both positive and negative aspects that influence clinicians' perception toward the AI. Results from quantitative analysis indicate that providing more AI explanations enhances user trust but also increases system complexity. Qualitative analysis indicates the potential of integrating such systems into the current diagnostic and screening workflow, but also highlights existing limitations including clinicians' reduced familiarity with AI/ML systems and the need for user-friendly and intuitive visualizations of speech information.

关键词： Decision support systems Explainable AI Statistical analysis Collaboration Depression Complexity theory Usability Bioinformatics

来源：评论

学校读者我要写书评

暂无评论

Automated classification of renal tumors on ultrasound images using deep neural network 9

Automated classification of renal tumors on ultrasound image...

引用

9th International Conference on Intelligent Informatics and BioMedical sciences, ICIIBMS 2024

作者： Wu, Wei-Chieh Chiang, Te-Mei Tsai, Zhi-Ren Asia University Program in Artificial Intelligence College of Information and Electrical Engineering Taichung City Taiwan Asia University Hospital Department of Radiation Oncology Taichung City Taiwan Asia University Department of Computer Science & Information Engineering Taiwan

ISBN: (纸本)9798350363043

Kidney cancer is one of the most common cancers worldwide. The major types of malignant renal tumors are renal cell carcinoma and urothelial carcinoma. Although the majority of renal tumors are malignant, up to 20% are benign, most commonly renal cyst and angiomyolipomas. Ultrasound is the most accessible imaging tool in medical practice, but it highly depends on operator skill, which may lead to high false-negative rate in diagnosis. The purpose of this study was to develop a predictive model for the automated classification of renal tumors on ultrasound images using deep neural network. A total of 880 kidney ultrasound images were used for training and testing. Transfer learning was used to the ten Convolution neural network models. The kidney ultrasound images were classified as benign or malignant tumors. The classification performance of the model was evaluated by sensitivity and specificity. The research results show that VGG18 yielded the best performance, with a sensitivity of 79%, and a specificity of 86%. © 2024 IEEE.

关键词： Ultrasonic imaging

来源：评论

学校读者我要写书评

暂无评论

Are LLMs Aware that Some Questions are not Open-ended?

Are LLMs Aware that Some Questions are not Open-ended?

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Yang, Dongjie 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 Shanghai Key Laboratory of Trusted Data Circulation and Governance in Web3 China

ISBN: (纸本)9798891761681

Large Language Models (LLMs) have shown the impressive capability of answering questions in a wide range of scenarios. However, when LLMs face different types of questions, it is worth exploring whether LLMs are aware that some questions have limited answers and need to respond more deterministically but some do not. We refer to this as question awareness of LLMs. The lack of question awareness in LLMs leads to two phenomena that LLMs are: (1) too casual to answer non-open-ended questions or (2) too boring to answer open-ended questions. In this paper, we first evaluate the question awareness in LLMs. The experimental results show that LLMs have the issues of lacking awareness of questions in certain domains, e.g. factual knowledge, resulting in hallucinations during the generation. To mitigate these, we propose a method called Question Awareness Temperature Sampling (QuATS). This method enhances the question awareness of LLMs by adaptively adjusting the output distributions based on question features. The automatic adjustment in QuATS eliminates the need for manual temperature tuning in text generation and consistently improves model performance in various benchmarks. © 2024 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Classification of Acute Intracerebral Hemorrhage Using Radiomics on Brain Computed Tomography Images 15

Classification of Acute Intracerebral Hemorrhage Using Radio...

引用

15th International Conference on Information Technology and Electrical engineering, ICITEE 2023

作者： Thabarsa, Phattanun Angkurawaranon, Salita Madla, Chakri Vuthiwong, Withawat Unsrisong, Kittisak Inkeaw, Papangkorn Chiang Mai University Program in Data Science Faculty of Engineering Chiang Mai Thailand Chiang Mai University Faculty of Medicine Department of Radiology Chiang Mai Thailand Chiang Mai University Data Science Research Center Faculty of Science Department of Computer Science Chiang Mai Thailand

ISBN: (纸本)9798350304466

Acute intracerebral hemorrhage (ICH) entity accounts for 10 to 15% of all strokes and is associated with a higher mortality rate ischemic stroke or subarachnoid hemorrhage. Causes of ICH are divided into primary, and secondary, including vascular malformation and tumorous. Primary ICH accounts for approximately 80% of all ICH cases. Vascular anomalies rank as the second most common cause of spontaneous ICH overall. Furthermore, hemorrhage resulting from brain tumors can occur in up to 10% of all primary or metastatic tumors. Early recognizing of these three causes of bleeding is critical for clinicians in precise diagnosis, effective treatment management, and helps avoid delayed diagnosis. We proposed a radiomics approach for classifying multiple causes of acute ICH as vascular malformation, tumorous, and primary-related hematoma. Non-contrast brain computed tomography with clinical features was used as input. The regions of both hematoma and perihematomal edema were delineated by using manual segmentation approach. Four feature selection methods were adopted. Also, three classification models were investigated in this study. The results showed that using the features selected by F-value applied with SVM classifier outperformed the other models, achieving weighted average accuracy (± SD) of 0.84 (± 0.07). Additionally, the model demonstrated average sensitivity and positive predictive value of 0.84 (± 0.06) and 0.86 (± 0.05), respectively. We also evaluate the overall performance of discriminating each class from the rest using AUC. The result suggested that our proposed model achieved the weighted average AUC of 0.90. Our proposed method highlights the potential in identifying multiple causes of acute and nontraumatic ICH, which has not been previously explored. © 2023 IEEE.

关键词： Brain

来源：评论

学校读者我要写书评

暂无评论

Smart Home Security System Using Face Recognition Based on IoT- CNN 2

Smart Home Security System Using Face Recognition Based on I...

引用

2nd International Conference on Information Technology Research and Innovation, ICITRI 2023

作者： Febriantono, M. Aldiki Zuhair, Alvin Khaeruddin School of Computer Science Bina Nusantara University Computer Science Department Jakarta11480 Indonesia University of Islam Blitar Electrical Engineering Department Blitar Indonesia University of Muhammadiyah Malang Diploma III Electronic Technology Vocational Study Program Malang Indonesia

ISBN: (纸本)9798350324945

Home security is a crucial aspect that requires careful attention, particularly when it comes to addressing theft concerns. Hence, implementing smart door technology equipped with facial recognition holds promising potential for enhancing home security. This study aims to develop a more secure and regulated home entry system by leveraging Internet of Things (IoT) technology and Machine Learning computer Vision for facial recognition. The system integrates IoT devices, such as cameras and automatic doors, wherein facial image data is captured by the camera and processed using the Convolutional Neural Network (CNN) algorithm to identify individuals. Once an individual is recognized, the system grants access to the home through an automated door. By relying on facial features, the system effectively restricts unauthorized access and safeguards homes against theft risks. Therefore, the advancement of a safer and more controlled home entry system utilizing IoT technology and Machine Learning computer Vision holds tremendous benefits for homeowners. © 2023 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

A Novel Hybrid Framework for Energy-Efficient Clustering and Routing in Heterogeneous IoT-Driven Wireless Sensor Networks 7

A Novel Hybrid Framework for Energy-Efficient Clustering and...

引用

7th International Conference on Contemporary Computing and Informatics, IC3I 2024

作者： Gupta, Gopal Kumar Jain, Arpit Sharma, Khemraj Ashok Kumar, P.M. Gupta, Shubhi Agarwal, Sheenu Nagpur Campus Pune440008 India Koneru Lakshmaiah Education Foundation Department of Computer Science Engineering AP Vaddeswaram522502 India Nanhua University Program in Management Sciences Department of Business Administration Dalin Chiayi62248 Taiwan Amity University Department of Computer Science and Engineering Uttar Pradesh Greater Noida India Uttarakhand Technical University Department of Electronics and Communication Engineering U.K. Dehradun India

ISBN: (纸本)9798350350067

Smart computing has been particularly notable in the development of wireless sensor networks (WSNs), which have many applications. Battery-powered, self-configuring sensor nodes are the basis of these networks. Energy and resources are limited when it comes to sensors. Unbalanced nodes in the network consume more power, which adversely affects the network's lifespan. An improved energy-efficient cluster-based routing protocol for heterogeneous wireless sensor networks (WSNs) based on the Internet of Things is proposed in this study. Several performance metrics were used to evaluate the proposed model's effectiveness, including energy efficiency, alive nodes, dead nodes, network lifetime, and residual energy. The results of the comparison were compared with existing methodologies, such as LEACH, PSO, and hybrid PSO. The proposed approach outperforms the existing model by a substantial margin in networks with 50 and 100 nodes, according to the simulation results. © 2024 IEEE.

关键词： Sensor nodes

来源：评论

学校读者我要写书评

暂无评论

Predicting Microsatellite Instability from Histology Images with Dilated Neighborhood Attention Transformer in Colorectal Cancer 24

Predicting Microsatellite Instability from Histology Images ...

引用

24th IEEE International Conference on Bioinformatics and Bioengineering, BIBE 2024

作者： Chen, Yun-Chi Chao, Tung Phandita, Wimaya Nitya Sun, Tzu-Yu Wang, Huai-Zhi Hsieh, Yi-Hsien Hsu, Le-Yin Lin, Che Taipei Taiwan College of Bioresources and Agriculture NTU Taipei Taiwan National Taiwan University of Science and Technology Department of Computer Science and Information Engineering Taipei Taiwan Graduate Institute of Communication Engineering NTU Taipei Taiwan NTU Data Science Degree Program Taipei Taiwan NTU Department of Electrical Engineering Taipei Taiwan Center for Advanced Computing and Imaging in Biomedicine NTU Taipei Taiwan NTU Smart Medicine and Health Informatics Program Taipei Taiwan

ISBN: (纸本)9798331518622

Microsatellite instability (MSI) is a pivotal genetic marker influencing the efficacy of immunotherapy in colorectal cancer. Traditional MSI examination often requires additional genetic or immunohistochemical tests, whereas histology images, widely available in colorectal cancer diagnosis, offer a valuable alternative for MSI prediction. Although Transformer-based models have demonstrated promising outcomes in predicting MSI from histology images, they are hampered by traditional local attention mechanisms that struggle to capture long-range interdependencies and establish a comprehensive global receptive field. In this study, we introduce DiNAT-MSI, a novel framework for histology-based MSI prediction that incorporates the Dilated Neighborhood Attention Transformer (DiNAT). This model enhances global context recognition and substantially expands receptive fields, all without additional computational burden. Our results demonstrate that DiNAT-MSI achieves a superior patientwise AUROC compared to ResNet18 and Swin Transformer, along with commendable explainability. Our work not only illustrates a more accessible diagnostic tool for leveraging histological data but also underscores the potential of Transformerbased models with sophisticated attention designs in advancing precision medicine for colorectal cancer patients. © 2024 IEEE.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Thermal energy dependent transient permittivity of epsilon-near-zero material

引用

science China(Physics,Mechanics & Astronomy) 2022年第8期65卷 96-101页

作者： Heng Wang Lixun Sun Kang Du Wending Zhang SooJin Chua Guixin Li Ting Mei MOE Key Laboratory of Material Physics and Chemistry under Extraordinary Conditions and Shaanxi Key Laboratory of Optical Information TechnologySchool of Physical Science and TechnologyNorthwestern Polytechnical UniversityXi’an710129China Department of Materials Science and Engineering Southern University of Science and TechnologyShenzhen518055China Shenzhen Institute for Quantum Science and Engineering Southern University of Science and TechnologyShenzhen518055China Department of Electrical and Computer Engineering National University of SingaporeSingapore117583Singapore LEES Program Singapore-MIT Alliance for Research&Technology(SMART)Singapore138602Singapore

Transparent conductive oxides exhibit attractive optical nonlinearity with ultrafast response and giant refractive index change near the epsilon-near-zero(ENZ) wavelength, originating from the intraband dynamics of conduction electrons. The optical nonlinearity of ENZ materials has been explained by using the overall-effective-mass and the overall-scattering-time of electrons in the extended Drude model. However, their response to optical excitation is yet the last building block to complete the theory. In this paper, the concept of thermal energy is theoretically proposed to account for the total energy of conduction electrons exceeding their thermal equilibrium value. The time-varying thermal energy is adopted to describe the transient optical response of indium-tin-oxide(ITO), a typical ENZ material. A spectrally-resolved femtosecond pump-probe experiment was conducted to verify our theory. By correlating the thermal energy with the pumping density, both the giant change and the transient response of the permittivity of ITO can be predicted. The results in this work provide a new methodology to describe the transient permittivities of ENZ materials, which will benefit the design of ENZ-based nonlinear photonic devices.

关键词： epsilon-near-zero optical nonlinearity transient response thermal energy hot electron indium tin oxide

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

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

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：