检索结果-内蒙古大学图书馆

2024 Findings of the Association for Computational Linguistics, EMNLP 2024

作者： Gu, Zhouhong Zhang, Lin Zhu, Xiaoxuan Chen, Jiangjie Huang, Wenhao Zhang, Yikai Wang, Shusen Ye, Zheyu Gao, Yan Xiao, Yanghua Feng, Hongwei Shanghai Key Laboratory of Data Science School of Computer Science Fudan University China Meta United States Xiaohongshu Inc. China

ISBN: (纸本)9798891761681

Detecting evidence within the context is a key step in the process of reasoning task. Evaluating and enhancing the capabilities of LLMs in evidence detection will strengthen context-based reasoning performance. This paper proposes a benchmark called DetectBench for verifying the ability to detect and piece together implicit evidence within a long context. DetectBench contains 3,928 multiple-choice questions, with an average of 994 tokens per question. Each question contains an average of 4.55 pieces of implicit evidence, and solving the problem typically requires 7.62 logical jumps to find the correct answer. To enhance the performance of LLMs in evidence detection, this paper proposes Detective Reasoning Prompt and Finetune. Experiments demonstrate that the existing LLMs' abilities to detect evidence in long contexts are far inferior to humans. However, the Detective Reasoning Prompt effectively enhances the capability of powerful LLMs in evidence detection, while the Finetuning method shows significant effects in enhancing the performance of weaker LLMs. Moreover, when the abilities of LLMs in evidence detection are improved, their final reasoning performance is also enhanced accordingly. The benchmark is available in https://***/MikeGu721/DetectBench. © 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

MedLogic-AQA: Enhancing Medical Question Answering with Abstractive Models Focusing on Logical Structures

MedLogic-AQA: Enhancing Medical Question Answering with Abst...

引用

2024 Findings of the Association for Computational Linguistics, EMNLP 2024

作者： Zafar, Aizan Mishra, Kshitij Ekbal, Asif Department of Computer Science and Engineering Indian Institute of Technology Patna India School of AI and Data Science Indian Institute of Technology Jodhpur India

ISBN: (纸本)9798891761681

In Medical question-answering (QA) tasks, the need for effective systems is pivotal in delivering accurate responses to intricate medical queries. However, existing approaches often struggle to grasp the intricate logical structures and relationships inherent in medical contexts, thus limiting their capacity to furnish precise and nuanced answers. In this work, we address this gap by proposing a novel Abstractive QA system MEDLOGIC-AQA that harnesses First Order Logic (FOL) based rules extracted from both context and questions to generate well-grounded answers. Through initial experimentation, we identified six pertinent first-order logical rules, which were then used to train a Logic-Understanding (LU) model capable of generating logical triples for a given context, question, and answer. These logic triples are then integrated into the training of MEDLOGIC-AQA, enabling effective and coherent reasoning during answer generation. This distinctive fusion of logical reasoning with abstractive QA equips our system to produce answers that are logically sound, relevant, and engaging. Evaluation with respect to both automated and human-based demonstrates the robustness of MEDLOGIC-AQA against strong baselines. Through empirical assessments and case studies, we validate the efficacy of MEDLOGIC-AQA in elevating the quality and comprehensiveness of answers in terms of reasoning as well as informativeness. © 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

Consistency-aware unsupervised label learning for cross-domain person re-identification

引用

Multimedia Tools and Applications 2024年 1-20页

作者： Geng, Yanbing Lian, Yongjian Cui, Fangshu Zhang, Xiaowei Zhou, Mingliang Zhang, Geao School of Data Science and Technology North University of China Shanxi Taiyuan030051 China Shandong Key Laboratory of Intelligent Information Processing School of Computer Science and Technology Qingdao University Qingdao266071 China School of Computer Science Chongqing University 174 Shazheng Street Shapingba District Chongqing400044 China College of Information Science and Engineering Northeastern University 11 Lane 3 Wenhua Road Heping District Liaoning Shenyang110819 China

Un-refined pseudo labels always disturb the cross-domain Re-ID performance in unsupervised clustering methods. In this paper, we propose a consistency-aware unsupervised label learning network to refine noisy labels for promising domain adaptation. Specifically, we use a hetero-generated label consistency constraint to mine possible label information, keep a reference consistency of the target pairs on the relative comparative characteristics. We then use a cross-granularity attention consistency constraint to refine the pseudo labels meanwhile learning multi-granularity discriminative representation, keeping a self-similarity consistency of the corresponding parts on the discriminative regions. Our model is fine-tuned by the refined pseudo-labels to reduce the domain gap while coping with the intra-domain variation. Experimental results demonstrate that the proposed method can achieve superior performance on several benchmark datasets. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Standard Multi-Layer Perceptron on Positive - Unlabeled Glycosylation Site dataset 8

Standard Multi-Layer Perceptron on Positive - Unlabeled Glyc...

引用

8th International Conference on computer science and Computational Intelligence, ICCSCI 2023

作者： Mahesworo, Bharuno Cenggoro, Tjeng Wawan Lumbanraja, Favorisen Rosyking Pardamean, Bens Statistics Department School of Computer Science Bina Nusantara University Indonesia Bioinformatics Data Science Research Center Bina Nusantara University Indonesia Computer Science Department School of Computer Science Bina Nusantara University Indonesia Computer Science Department School of Matematics and Natural Science University of Lampung Indonesia

The implementation of computational approaches for protein glycosylation site prediction is becoming popular since the experimental-validated glycosylation data became more abundant. Some of the data were found to be wrong after the experiment was again carried out with more sophisticated technology. To solve this issue, the latest state-of-the-art model trained the model based on a positive-unlabelled algorithm. The aim of this research is to explore the possibility of an approach applying a simple neural network algorithm and still achieve high classification performance. The model proposed in this research gave competitive results with fewer preprocessing steps. Increasing the accuracy of glycosylation site prediction can complement laboratory-based methods and is very useful for understanding the role of glycosylation. © 2023 The Authors. Published by Elsevier B.V.

关键词： Glycosylation PTM Site Prediction Standard Multi-Layer Perceptron

来源：评论

学校读者我要写书评

暂无评论

ConvNeXt Model for Breast Cancer Image Classification 6

ConvNeXt Model for Breast Cancer Image Classification

引用

6th International Conference on Cybernetics and Intelligent System, ICORIS 2024

作者： Setiawan, Devin Karnyoto, Andrea Stevens Intan, Indo Pardamean, Bens Department of Electrical Engineering and Computer Science University of Kansas Lawrence United States Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta Indonesia Department of Informatics Engineering Universitas Dipa Makassar Makassar Indonesia Computer Science Department BINUS Graduate Program Computer Science Program Bina Nusantara University Jakarta Indonesia

ISBN: (纸本)9798331539603

Breast cancer is an occurrence of cancer that attacks breast tissue and is the most common cancer among women worldwide, affecting one in eight women. In this modern world, breast cancer image classification simplifies the process of analyzing, providing objective and accurate results. By leveraging machine learning algorithms and computer vision techniques, we developed breast cancer detection. The dataset is histopathology dataset from BreakHis and UNHAS Hospital. We chose the ConvNeXt-Tiny model then modified the classifier head as the proposed method. Before the dataset is processed by the model, we augment the images by applying random horizontal and vertical flips, adjustments to brightness, contrast, saturation, and hue using color jitter. The augmentation process simulates real-world variance and enhances the model's ability to generalize to unseen data. Our proposed model gained better performance (accuracy, F1-Score) results compared two other techniques to VGG16 and SVM. According to our experiments, the F1-Score for the ConvNeXt-Tiny model with classifier head modification is higher at 0.9516, than the gain for VGG16 at 0.9292, and the gain for the SVM at 0.83. © 2024 IEEE.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

Refined Coreset Selection: Towards Minimal Coreset Size under Model Performance Constraints 41

Refined Coreset Selection: Towards Minimal Coreset Size unde...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Xia, Xiaobo Liu, Jiale Zhang, Shaokun Wu, Qingyun Wei, Hongxin Liu, Tongliang School of Computer Science The University of Sydney Australia College of Information Science and Technology Penn State University United States Department of Statistics and Data Science Southern University of Science and Technology China

Coreset selection is powerful in reducing computational costs and accelerating data processing for deep learning algorithms. It strives to identify a small subset from large-scale data, so that training only on the subset practically performs on par with full data. Practitioners regularly desire to identify the smallest possible coreset in realistic scenes while maintaining comparable model performance, to minimize costs and maximize acceleration. Motivated by this desideratum, for the first time, we pose the problem of refined coreset selection, in which the minimal coreset size under model performance constraints is explored. Moreover, to address this problem, we propose an innovative method, which maintains optimization priority order over the model performance and coreset size, and efficiently optimizes them in the coreset selection procedure. Theoretically, we provide the convergence guarantee of the proposed method. Empirically, extensive experiments confirm its superiority compared with previous strategies, often yielding better model performance with smaller coreset sizes. The implementation is available at https://***/xiaoboxia/LBCS. Copyright 2024 by the author(s)

关键词：

来源：评论

学校读者我要写书评

暂无评论

Feature Selection for GPSR Based on Maximal Information Coefficient and Shapley Values 13

Feature Selection for GPSR Based on Maximal Information Coef...

引用

13th IEEE Congress on Evolutionary Computation, CEC 2024

作者： Rimas, Mohamad Anfar, Mohamad Chen, Qi Zhang, Mengjie School of Engineering and Computer Science Victoria University of Wellington Centre for Data Science and Artificial Intelligence PO Box 600 Wellington New Zealand

ISBN: (纸本)9798350308365

Feature selection is a critical aspect of improving the interpretability of machine learning models. Genetic programming (GP) has a built-in feature selection mechanism that explores the search space to include informative features in models. However, this built-in mechanism is insufficient for identifying important features, when dealing with high-dimensional feature spaces. To overcome this limitation, the paper introduces a novel feature importance measurement based on the Maximal Infor-mation Coefficient and Shapley Values. The proposed algorithm operates in two stages. In the first stage, it identifies the best individuals from different populations. In the second stage, the best individuals from the first stage are utilized for the calculation of the novel individual feature importance measurement. The new feature importance measurement offers valuable insights into the significance and relevance of the selected features. Regression experiments were conducted on six datasets to assess the effectiveness of the proposed method. Furthermore, comparisons were made with two other algorithms to evaluate its performance. The results indicate that the proposed approach enhances GP performance for high dimensional datasets while maintaining GP trees of similar size compared to standard GP. © 2024 IEEE.

关键词： Genetic programming

来源：评论

学校读者我要写书评

暂无评论

Implementation of Face Patterns and Smile Recognition for Intelligent Class Attendance Systems 6

Implementation of Face Patterns and Smile Recognition for In...

引用

6th International Conference on computer and Informatics Engineering, IC2IE 2023

作者： Miftakhurrokhmat Suparyanto, Teddy Elwirehardja, Gregorius Natanael Karimah, Shofiyati Nur Pardamean, Bens Bina Nusantara University Bioinformatics and Data Science Research Center Jakarta Indonesia School of Computer Science Bina Nusantara University Computer Science Department Jakarta Indonesia Universitas Amikom Yogyakarta Faculty of Computer Science Department of Informatics Yogyakarta Indonesia Bina Nusantara University Binus Graduate Program - Master of Computer Science Computer Science Department Jakarta Indonesia

ISBN: (纸本)9798350345162

Students 'attendance in class is one important success parameter in face-to-face learning processes. Conventional attendance systems, such as paper-based attendance sheets or identity card systems, require a long time in the manual recapitulation process. Without additional verifications, even computer vision-based methods are prone to fraudulent practices by the students instead of gaining their excitement and attention in a class. To stimulate students' attention in a class, this work designs an intelligent class attendance system, in which facial pattern and smile recognition are implemented by using the latter as an additional task-based verification to reduce the risks of fake attendance. For the face recognition module, this pilot study used FaceNet as a feature extractor combined with SVM for classification, whereas the Haar cascade algorithm is used for recognizing smiles. This face recognition pipeline was implemented as a service installed on minicomputers or Internet of Things (IoT) devices in each classroom and connected to an IP camera. Every recorded attendance will be sent as a notification to a mobile application for students that requires their active participation to confirm it with a smiling self-photo. The proposed pipeline obtained 92.86% accuracy on the test data, and 66.67% accuracy when evaluated in a real-life simulation setting through the implemented system. The lower accuracy in the simulation indicated that further improvements are indispensable, especially since the model obtained 28.57% False Negative Rate. Future studies will need to acquire more data and experiment with more efficient methods of attendance verification. © 2023 IEEE.

关键词： class attendance convolutional neural network deep learning face recognition smile

来源：评论

学校读者我要写书评

暂无评论

ABLE: Personalized Disability Support with Politeness and Empathy Integration

ABLE: Personalized Disability Support with Politeness and Em...

引用

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

作者： Mishra, Kshitij Burja, Manisha Ekbal, Asif Department of Computer Science and Engineering Indian Institute of Technology Patna India School of AI and Data Science Indian Institute of Technology Jodhpur India

ISBN: (纸本)9798891761643

In today's dynamic world, providing inclusive and personalized support for individuals with physical disabilities is imperative. With diverse needs and preferences, tailored assistance according to user personas is crucial. In this paper, we introduce ABLE (Adaptive, Bespoke, Listen and Empathetic), a Conversational Support System for Physical Disabilities. By tracking user personas, including gender, age, and personality traits based on the OCEAN model, ABLE ensures that support interactions are uniquely tailored to each user's characteristics and preferences. Moreover, integrating politeness and empathy levels in responses enhances user satisfaction and engagement, fostering a supportive and respectful environment. The development of ABLE involves compiling a comprehensive conversational dataset enriched with user profile annotations. Leveraging reinforcement learning techniques and diverse reward mechanisms, ABLE trains a model to generate responses aligned with individual user profiles while maintaining appropriate levels of politeness and empathy. Based on rigorous empirical analysis encompassing automatic and human evaluation metrics based on persona-consistency, politeness accuracy, empathy accuracy, perplexity, and conversation coherence, the efficacy of ABLE is assessed. Our findings underscore ABLE's success in delivering tailored support to individuals grappling with physical disabilities. To the best of our knowledge, this is the very first attempt towards building a user's persona-oriented physical disability support system. © 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

AI-Based Video Analysis for Driver Fatigue Detection: A Literature Review on Underlying datasets, Labelling, and Alertness Level Classification 1

引用

International Conference on Innovative Technologies in Intelligent Systems and Industrial Applications, CITISIA 2022

作者： Ariansyah, Dedy Rahutomo, Reza Elwirehardja, Gregorius Natanael Asadi, Faisal Pardamean, Bens Bioinformatics and Data Science Research Centre Bina Nusantara University Jakarta11480 Indonesia Computer Science Department BINUS Graduate Program Master of Computer Science Program Bina Nusantara University Jakarta11480 Indonesia

ISBN: (数字)9783031290787

ISBN: (纸本)9783031290770

Reduced alertness because of fatigue or drowsiness accounts for a major cause of road accidents globally. To minimize the likelihood of alertness reduction-related crashes, a video-based detection emerges as a non-intrusive method and can offer high accuracy for the countermeasure development. Many Artificial Intelligence (AI) techniques have been developed to aid in video analysis for fatigue detection. However, the issues in AI-based video analysis for fatigue countermeasure development are rarely discussed. This paper reviews current video-based countermeasure development in the literature and highlights some reliability issues of AI-based fatigue countermeasure development in terms of underlying dataset, labelling method, and alertness level classification. The result serves as insights and consideration to academics and industrialists in developing a high reliable AI-based video analysis for driver fatigue countermeasure. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Classification (of information)

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：