检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Jeong, Soyeong Baek, Jinheon Park, ChaeHun Park, Jong C. School of Computing Korea Advanced Institute of Science and Technology Graduate School of AI Korea Advanced Institute of Science and Technology

One of the challenges in information retrieval (IR) is the vocabulary mismatch problem, which happens when the terms between queries and documents are lexically different but semantically similar. While recent work has proposed to expand the queries or documents by enriching their representations with additional relevant terms to address this challenge, they usually require a large volume of query-document pairs to train an expansion model. In this paper, we propose an Unsupervised Document Expansion with Generation (UDEG) framework with a pretrained language model, which generates diverse supplementary sentences for the original document without using labels on query-document pairs for training. For generating sentences, we further stochastically perturb their embeddings to generate more diverse sentences for document expansion. We validate our framework on two standard IR benchmark datasets. The results show that our framework significantly outperforms relevant expansion baselines for IR. Copyright © 2021, The Authors. All rights reserved.

关键词： Information retrieval

来源：评论

学校读者我要写书评

暂无评论

An Adaptive Update Algorithm for Fingerprint Database Based on Validity Detection 6

An Adaptive Update Algorithm for Fingerprint Database Based ...

引用

6th International Conference on Automation, Control and Robots, ICACR 2022

作者： Zhang, Chenxin Chen, Xin Xu, Xueting Peng, Ao Xiamen University The National Joint Engineering Center of Navigation and Location-Based-Service Technology Xiamen China Xi'an Jiaotong-Liverpool University School of Ai and Advanced Computing Suzhou China Xiamen University School of Informatics Xiamen China

ISBN: (数字)9781665498739

ISBN: (纸本)9781665498739

Maintaining the accuracy of fingerprint-based indoor positioning requires ensuring the validity of the fingerprint database. The main task of fingerprint database maintenance is to detect and update invalid data in a timely manner. In this paper, we address the problem of invalid fingerprint data with the fingerprint matching effectiveness evaluation method and the adaptive update algorithm of fingerprint database. The experimental design and field data collection and analysis were conducted in two typical experimental scenarios: an indoor basketball court and an indoor school building. Experiments with real measurements show that the proposed algorithm improves the performance of updating the fingerprint database in real time and robustness. © 2022 IEEE.

关键词： Database systems

来源：评论

学校读者我要写书评

暂无评论

DGPDHGCN: A Heterogeneous Graph Convolutional Network Method for Predicting Drug-Disease Associations

DGPDHGCN: A Heterogeneous Graph Convolutional Network Method...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Zhu, Haoran Yu, Tong Ge, Ling Wang, Jianjia Xi'an Jiaotong-Liverpool University School of Ai and Advanced Computing Xjtlu Entrepreneur College Suzhou China Shanghai University School of Computer Engineering and Science China Huaibei People's Hospital Department of Clinical Laboratory Huaibei China

ISBN: (纸本)9798350386226

Drug repositioning is a crucial aspect of biomedical research, and predicting drug-disease associations (DDAs) is a critical step in this process. With the development of deep learning and neural network technologies, Graph Convolutional Networks (GCNs) have achieved significant performances in this research field. Although existing DDAs models have made substantial progress, there is still need for improvement in sufficiently utilizing and integrating information from multiple biological entities. In this study, we propose a Drug-Gene-Protein-Disease Heterogeneous Graph Convolutional Network (DGPDHGCN) model for drug-disease association prediction. First, we construct a heterogeneous network from multiple data sources and establish meta-paths based on the topological information of biological entities. Then, the DGPDHGCN model learns representations of drugs and diseases from similarity and association data of those entities. Finally, we define a score function to quantify the associations between drugs and diseases. Through extensive experiments, we demonstrate that DGPDHGCN outperforms baseline models in DDAs prediction tasks in terms of metrics such as AUPR, F1-score, precision, and recall. The source code and experimental datasets can be found in https://***/Saxon0918/DGPDHGCN © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Diversity-oriented Contrastive Learning for RGB-T Scene Parsing 2

Diversity-oriented Contrastive Learning for RGB-T Scene Pars...

引用

2nd International Conference on Sensing, Measurement, Communication and Internet of Things Technologies, SMC-IoT 2023

作者： Liu, Hengyan Ren, Guangyu Dai, Tianhong Zhang, Di Xu, Pengjing Zhang, Wenzhang Hu, Bintao Xi'an Jiaotong-Liverpool University School of Ai and Advanced Computing Suzhou China Imperial College London Department of Electrical and Electronic Engineering London United Kingdom University of Aberdeen Department of Computing Science Aberdeen United Kingdom Xi'an Jiaotong-Liverpool University School of Internet of Things Suzhou China

ISBN: (纸本)9798350373257

Scene parsing gains improvement under poor lighting conditions by leveraging complementary information from thermal images. However, there are inherent gaps between different modalities and most existing methods propose network modules to reduce the gap. Contrastive learning has gained prominence in the field of computer vision by enabling models to capture rich feature representations through the comparison of positive and negative samples. To extend its applicability to scene parsing, we propose a unique method to enhance the effectiveness of semantic segmentation without negative samples. A determinantal point processes (DPP) based method is proposed to minimize the similarity between relevant image inputs, specifically focusing on learning the intrinsic features between RGB and its thermal images. We further consider the deployment of this task and introduce an efficient vision transformer as a backbone for feature extraction. Our final model achieves a reasonable balance between model size and accuracy. © 2023 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

A New Method for WFOV Camera Distortion Correction 5

A New Method for WFOV Camera Distortion Correction

引用

5th World Robot Conference Symposium on advanced Robotics and Automation, WRC SARA 2023

作者： Chen, Qian Wei, Zhaoxiang Tan, Xinyuan Shen, Hongbin Meng, Cai Beihang University Image Processing Center School of Astronautics China Beihang University Beijing Advanced Innovation Center for Biomedical Engineering China Vison-BHU Joint AI+Computing Optics Laboratory China

ISBN: (纸本)9798350307320

In laparoscopic surgery, the laparoscope has the advantage of a small volume and a large field of view, but their obvious distortion affect the doctor's judgment. aimed at this limitation, we proposed a novel method to correct the image distortion while preserving the majority of the peripheral information. At first, a box-shaped surface is introduced before the lens to effectively capture the incident light from the fisheye image. Then, all the image pixels are mapped onto this boxshaped surface. Next, the image plane and the focal point are adjusted, moving them backward, and the pixels on the boxshaped surface are then re-projected onto the final focal plane to generate the corrected image. To verify the feasibility, the proposed method is compared with several classical approaches in terms of two designed comprehensive evaluation metrics, namely the signal retention rate (SRR) and the Offset of Hough Space Histogram (OHSH). The results demonstrate that the proposed method surpasses other classical methods both in SRR and OHSH. © 2023 IEEE.

关键词： Laparoscopy

来源：评论

学校读者我要写书评

暂无评论

Question Answering with Language Models 12

Question Answering with Language Models

引用

12th IEEE Conference on Systems, Process and Control, ICSPC 2024

作者： Wong, Jia Yin Lee, Chin Poo Lim, Kian Ming Lim, Jit Yan Mogan, Jashila Nair Multimedia University Faculty of Info.Science & Technology Melaka Malaysia Xi'an Jiaotong Liverpool University School of AI and Advanced Computing Jiangsu Province China University of Nottingham Ningbo China School of Computer Science Zhejiang Province China

ISBN: (纸本)9798350391398

With the significant increase in the number of resources providing various types of information, ranging from thousands to millions of sources including research papers, blogs, and more, extracting and providing meaningful insights has become a challenge. This study develops a Question Answering (QA) system using the Haystack framework, capable of retrieving relevant documents and extracting answers from lengthy texts. The implemented QA system consists of four main components: an indexing pipeline, a document store, a searching pipeline, and an evaluation module. Additionally, this study investigates how different model architectures affect performance in retrieving and extracting answers. Two different retrievers, BM25 Retriever and Dense Passage Retriever, and five different readers, BERT, Roberta, albert, MiniLM, and ELECTRA, are examined. The models are tested and evaluated using the SQuAD datasets. The combination of BM25 Retriever and RoBERTa Reader achieved the best performance, with an F1-score of 0.9301 and an Exact Match score of 0.8956 on the SQuAD2.0 dataset. © 2024 IEEE.

关键词： Question answering

来源：评论

学校读者我要写书评

暂无评论

Guardians of Discourse: Evaluating LLMs on Multilingual Offensive Language Detection 10

Guardians of Discourse: Evaluating LLMs on Multilingual Offe...

引用

10th IEEE Smart World Congress, SWC 2024

作者： He, Jianfei Wang, Lilin Wang, Jiaying Liu, Zhenyu Na, Hongbin Wang, Zimu Wang, Wei Chen, Qi Xi'an Jiaotong-Liverpool University School of Ai and Advanced Computing Suzhou China Zhejiang University of Technology College of Computer Science and Technology Hangzhou China Australian Artificial Intelligence Institute University of Technology Sydney Sydney Australia Xi'an Jiaotong-Liverpool University School of Advanced Technology Suzhou China

ISBN: (纸本)9798331520861

Identifying offensive language is essential for maintaining safety and sustainability in the social media era. Though large language models (LLMs) have demonstrated encouraging potential in social media analytics, they lack thorough evaluation when in offensive language detection, particularly in multilingual environments. We for the first time evaluate multilingual offensive language detection of LLMs in three languages: English, Spanish, and German with three LLMs, GPT-3.5, Flan-T5, and Mistral, in both monolingual and multilingual settings. We further examine the impact of different prompt languages and augmented translation data for the task in non-English contexts. Furthermore, we discuss the impact of the inherent bias in LLMs and the datasets in the mispredictions related to sensitive topics. © 2024 IEEE.

关键词： Social networking (online)

来源：评论

学校读者我要写书评

暂无评论

Multivariate Time Series Spatial Extreme Clustering with Voformer-Ec Neural Networks

SSRN

引用

SSRN 2023年

作者： Xin, Ning Su, Jionglong Hasan, Md Maruf School of AI and Advanced Computing Xi’an Jiaotong-Liverpool University Jiangsu Suzhou215123 China

Droughts pose significant risks to global ecosystems and agriculture. Despite extensive research, accurate and efficient methods for monitoring drought and generalising based on observations remain elusive. Traditional multivariate time series clustering methods struggle to balance accurately analyzing the shape of time series data and maintaining fast clustering speed. This study introduces the Voformer-EC model as a novel approach to address this problem, enhancing the analysis of drought-related multivariate time series data. The Voformer-EC model simultaneously accounts for time series shape and operational efficiency, utilizing the Voformer architecture to extract time series features and implementing Extreme Clustering. Utilizing summer precipitation and temperature patterns from 2012 to 2014, the Voformer-EC model was applied to identify drought-prone regions and facilitate targeted risk mitigation strategies. The most drought-prone areas were identified through comprehensive analysis during the study period. The results demonstrate the model’s exceptional accuracy and efficiency, offering a powerful tool for informing interventions and enhancing resilience against drought impacts providing valuable insights into the spatial distribution of drought risk. © 2023, The Authors. All rights reserved.

关键词： Drought

来源：评论

学校读者我要写书评

暂无评论

Realistic Conversational Question Answering with Answer Selection based on Calibrated Confidence and Uncertainty Measurement

arXiv

引用

arXiv 2023年

作者： Jeong, Soyeong Baek, Jinheon Hwang, Sung Ju Park, Jong C. School of Computing Graduate School of AI United States Korea Advanced Institute of Science and Technology Korea Republic of

Conversational Question Answering (ConvQA) models aim at answering a question with its relevant paragraph and previous question-answer pairs that occurred during conversation multiple times. To apply such models to a real-world scenario, some existing work uses predicted answers, instead of unavailable ground-truth answers, as the conversation history for inference. However, since these models usually predict wrong answers, using all the predictions without filtering significantly hampers the model performance. To address this problem, we propose to filter out inaccurate answers in the conversation history based on their estimated confidences and uncertainties from the ConvQA model, without making any architectural changes. Moreover, to make the confidence and uncertainty values more reliable, we propose to further calibrate them, thereby smoothing the model predictions. We validate our models, Answer Selection-based realistic Conversation Question Answering, on two standard ConvQA datasets, and the results show that our models significantly outperform relevant baselines. Code is available at: https://***/starsuzi/AS-ConvQA. Copyright © 2023, The Authors. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

D4FT: A DEEP LEARNING APPROACH TO KOHN-SHAM DENSITY FUNCTIONAL THEORY 11

D4FT: A DEEP LEARNING APPROACH TO KOHN-SHAM DENSITY FUNCTION...

引用

11th International Conference on Learning Representations, ICLR 2023

作者： Li, Tianbo Lin, Min Hu, Zheyuan Zheng, Kunhao Vignale, Giovanni Kawaguchi, Kenji Neto, A.H. Castro Novoselov, Kostya S. Yan, Shuicheng SEA AI Lab China School of Computing National University of Singapore Singapore Institute for Functional Intelligent Materials National University of Singapore Singapore Centre for Advanced 2D Materials National University of Singapore Singapore

Kohn-Sham Density Functional Theory (KS-DFT) has been traditionally solved by the Self-Consistent Field (SCF) method. Behind the SCF loop is the physics intuition of solving a system of non-interactive single-electron wave functions under an effective potential. In this work, we propose a deep learning approach to KS-DFT. First, in contrast to the conventional SCF loop, we propose directly minimizing the total energy by reparameterizing the orthogonal constraint as a feed-forward computation. We prove that such an approach has the same expressivity as the SCF method yet reduces the computational complexity from O(N4) to O(N3). Second, the numerical integration, which involves a summation over the quadrature grids, can be amortized to the optimization steps. At each step, stochastic gradient descent (SGD) is performed with a sampled minibatch of the grids. Extensive experiments are carried out to demonstrate the advantage of our approach in terms of efficiency and stability. In addition, we show that our approach enables us to explore more complex neural-based wave functions. © 2023 11th International Conference on Learning Representations, ICLR 2023. All rights reserved.

关键词： Wave functions

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：