检索结果-内蒙古大学图书馆

17th International Congress on Image and signal processing, BioMedical Engineering and Informatics, CISP-BMEI 2024

作者： Xu, Wentong Fu, Chao Yu, Jing Si, Caifeng Li, Zuoyong Li, Chaochao Fan, Haoyi School of Computer and Artificial Intelligence Zhengzhou University Zhengzhou450001 China First Affiliated Hospital of Zhengzhou University Department of Ultrasound Henan Zhengzhou450052 China School of Computer and Big Data Minjiang University Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Fuzhou350121 China

ISBN: (纸本)9798331507398

Anomaly detection has been widely explored by training an out-of-distribution detector with only normal data. Medical image analysis, as a common tool, faces the challenge of how to further enhance the detection performance for thyroid cancer, especially with the application of various deep learning methods in the thyroid-related field. In this paper, we validate the effectiveness of sonographic feature descriptions (textual information) for thyroid cancer diagnosis. Building on this, we propose a simple multimodal self-supervised framework that leverages both textual and image modalities for thyroid cancer anomaly detection. Results on a private dataset demonstrate the effectiveness and superiority of our proposed method compared to advanced methods. © 2024 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Hybrid of Spans and Table-Filling for Aspect-Level Sentiment Triplet Extraction 30

Hybrid of Spans and Table-Filling for Aspect-Level Sentiment...

引用

Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024

作者： Nuo, Minghua Guo, Chaofan College of Computer Science Inner Mongolia University Inner Mongolia Hohhot010021 China National & Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian Inner Mongolia Hohhot010021 China Inner Mongolia Key Laboratory of Mongolian Information Processing Technology Inner Mongolia Hohhot010021 China

ISBN: (纸本)9782493814104

Aspect Sentiment Triplet Extraction (ASTE) has become an emerging task in sentiment analysis research. Recently, researchers have proposed different tagging schemes, containing tagging of words, tagging of word-pairs, and tagging of spans. However, the first two of these methods are often insufficient for the identification of multi-word terms, while the span tagging can label the entire phrase span, but it lacks the interactive information between words. In this paper, we propose Hybrid of Spans and Table-filling (S&T) model which combining span with table-filling. Specifically, S&T model achieve full fusion of syntactic and contextual features through cross-attention and generate the structures of word-pair table through Biaffine. Then, our model converts it to a span table by computing semantic distance based on syntactic dependency tree, which can enrich each unit of span table with semantic and interactive information. Meanwhile, the initial sentence features are constructed as simple phrase tables to enhance textual information of the phrase itself. In decoding, we define 8 types of labels for identifying three dimensions including aspect, opinion, and sentiment. Finally, the extensive experiments on widely-used dataset show S&T model achieves competitive results in ASTE task, the results certify the effectiveness and robustness of our S&T model. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Filling

来源：评论

学校读者我要写书评

暂无评论

GNEA: A Novel GCN-based Network Embedding Algorithm for Semantic Social Network 10

GNEA: A Novel GCN-based Network Embedding Algorithm for Sema...

引用

10th International Symposium on System Security, Safety, and Reliability, ISSSR 2024

作者： Zhao, Jinbo He, Jinling Du, Yuanhan Tang, Ming Xu, Xiaolong Nanjing University of Posts and Telecommunications Jiangsu Key Laboratory of Big Data Security and Intelligent Processing Nanjing China State Grid Jiangsu Electric Power Company Limited Nanjing China Nanjing University of Posts and Telecommunications School of Computer Science Nanjing China

ISBN: (纸本)9798350362930

With the development of semantic social networks, social networks become more complex and their size expands rapidly, which brings significant challenges to social network analysis. Network Embedding can transform the network from a high-dimensional adjacency matrix to a low-dimensional one, which has excellent foreground in link prediction, vertex classification, and graph visualization. Nowadays, most algorithms are proposed for static networks with little consideration of the dynamic changes in the network. However, most real-world networks change over time. Directly applying static network embedding algorithms to dynamic networks will result in poor stability, flexibility, and efficiency. Because of these shortcomings, we propose a graph convolution-based dynamic network representation learning algorithm (GNEA), which combines Graph Convolutional Network (GCN) with Long Short-Term Memory (LSTM) to train the time series networks. GCN is applied to extract features in the network, and LSTM is utilized to capture temporal information. GNEA can not only perform characterization learning on the network but also obtain more abundant information during the dynamic evolution of the network. GNEA is compared with several typical algorithms on the datasets Stochastic Block Model (SBM), Autonomous Systems (AS), and Digital Bibliography and Library Project (DBLP). The results prove that GNEA has good performance in MAP and precision@k. © 2024 IEEE.

关键词： Complex networks

来源：评论

学校读者我要写书评

暂无评论

Joint Image Restoration For Domain Adaptive Object Detection In Foggy Weather Condition

Joint Image Restoration For Domain Adaptive Object Detection...

引用

IEEE International Conference on Image processing

作者： Jing Ma Meng Lin Gang Zhou Zhenhong Jia School of Computer Science and Technology Xinjiang University Urumqi China Xinjiang Key Laboratory of Signal Detection and Processing Urumqi China

ISBN: (数字)9798350349399

ISBN: (纸本)9798350349405

Driven by deep learning, object detection methods have made significant progress in recent years. However, there is still a domain shift between synthetic foggy data and real foggy data, this leads to a undesirable decrease in detection results when applying the algorithm model trained on synthetic foggy datasets. In this article, we design a domain-adaptive YOLOX object detection algorithm by joint image restoration, in order to improve object detection performance in foggy scenes. Specially, we design an end-to-end domain adaptive framework that combines dehazing module and YOLOX together. To achieve feature alignment, we introduced a domain classifier in the feature spaceand discuss its optimal placement in the framework. Experimental results show that the proposed domain adaptation method achieved 62.60 percent mAP on real foggy image datasets RTTs, outperforming other state-of-the-art methods.

关键词： Deep learning Adaptation models Object detection Feature extraction Data models Image restoration Classification algorithms

来源：评论

学校读者我要写书评

暂无评论

Exploring the Compositional Deficiency of Large Language Models in Mathematical Reasoning Through Trap Problems

arXiv

引用

arXiv 2024年

作者： Zhao, Jun Tong, Jingqi Mou, Yurong Zhang, Ming Zhang, Qi Huang, Xuanjing School of Computer Science Fudan University China Shanghai Key Laboratory of Intelligent Information Processing Fudan University China

Human cognition exhibits systematic compositionality, the algebraic ability to generate infinite novel combinations from finite learned components, which is the key to understanding and reasoning about complex logic. In this work, we investigate the compositionality of large language models (LLMs) in mathematical reasoning. Specifically, we construct a new dataset MATHTRAP‡ by introducing carefully designed logical traps into the problem descriptions of MATH and GSM8K. Since problems with logical flaws are quite rare in the real world, these represent "unseen" cases to LLMs. Solving these requires the models to systematically compose (1) the mathematical knowledge involved in the original problems with (2) knowledge related to the introduced traps. Our experiments show that while LLMs possess both components of requisite knowledge, they do not spontaneously combine them to handle these novel cases. We explore several methods to mitigate this deficiency, such as natural language prompts, few-shot demonstrations, and fine-tuning. Additionally, we test the recently released OpenAI o1 model and find that human-like ‘slow thinking’ helps improve the compositionality of LLMs. Overall, systematic compositionality remains an open challenge for large language models. Copyright © 2024, The Authors. All rights reserved.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Meta-path and Meta-schema Hierarchical Aggregation for Heterogeneous Graph Neural Networks

Meta-path and Meta-schema Hierarchical Aggregation for Heter...

引用

Smart World Congress (SWC), IEEE

作者： Ling Wu Pingping Gao Kun Guo Fujian Key Laboratory of Network Computing and Intelligent Information Processing College of Computer and Data Sciencen (Fuzhou University) China

ISBN: (数字)9798331520861

ISBN: (纸本)9798331520878

With deep learning’s advancement in recent years, heterogeneous graph neural networks (HGNNs) have drawn a lot of interest. They are a group of deep learning models specifically designed for handling heterogeneous graph data, in which nodes and edges are of various types and all nodes are assumed to have either direct or indirect associations. A metaschema, which serves as a thorough and unified blueprint for the heterogeneous graph, elegantly connects varied node types to other heterogeneous nodes via multiple heterogeneous edges with rich sematincs. However, many existing methods that utilize meta-schema to mine heterogeneous information often focus on the different meta-relationships inside the schema, limiting the meta-schema to describing only the local relational semantics. To better utilize meta-schema for efficiently integrating different heterogeneous information, we organize them into a hierarchical structure(i.e., hierarchical meta-schema), with all types of nodes distributed across different layers. The layers are interconnected through heterogeneous relationships. The target type is placed at the final layer and others are arranged hierarchically in the front according to the heterogeneous relationships defined in the meta-schema. During information aggregation, according to the hierarchical meta-schema, the information of each layer is gradually aggregated to the target type on the final layer from far to near via the attention mechanism. Moreover, metapaths regularly begin and end with the same type and help to define complex structures and semantic. Therefore, we also consider the semantic information of neighbors based on metapaths within the proposed hierarchical meta-schema to enhance the complex semantics among nodes of the same-type that may be lacking in the meta-schema. Finally, we proposed a meta-path and meta-schema hierarchical aggregation for heterogeneous graph neural network model, named HGNN-MMHA. And we may allow the meta-schema to not

关键词： Deep learning Correlation Limiting Attention mechanisms Semantics Graph neural networks Heterogeneous networks Data models

来源：评论

学校读者我要写书评

暂无评论

Abstains from Prediction: Towards Robust Relation Extraction in Real World 21

Abstains from Prediction: Towards Robust Relation Extraction...

引用

21st China National Conference on Computational Linguistics, CCL 2022

作者： Zhao, Jun Zhang, Yongxin Xu, Nuo Gui, Tao Zhang, Qi Chen, Yunwen Gao, Xiang School of Computer Science Shanghai Key Laboratory of Intelligent Information Processing Fudan University Shanghai China Co. Ltd. Shanghai China

ISBN: (纸本)9783031183140

Supervised learning is a classic paradigm of relation extraction (RE). However, a well-performing model can still confidently make arbitrarily wrong predictions when exposed to samples of unseen relations. In this work, we propose a relation extraction method with rejection option to improve robustness to unseen relations. To enable the classifier to reject unseen relations, we introduce contrastive learning techniques and carefully design a set of class-preserving transformations to improve the discriminability between known and unseen relations. Based on the learned representation, inputs of unseen relations are assigned a low confidence score and rejected. Off-the-shelf open relation extraction (OpenRE) methods can be adopted to discover the potential relations in these rejected inputs. In addition, we find that the rejection can be further improved via readily available distantly supervised data. Experiments on two public datasets prove the effectiveness of our method capturing discriminative representations for unseen relation rejection. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

NetPrompt: Neural Network Prompting Enhances Event Extraction in Large Language Models

引用

IEEE Transactions on Big Data 2025年

作者： Mu, Lin Cheng, Yide Shen, Jun Zhang, Yiwen Zhong, Hong School of Computer Science and Technology Anhui University Anhui Hefei230601 China The Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education the Anhui Engineering Laboratory of IoT Security Technologies the School of Computer Science and Technology the Institute of Physical Science and Information Technology Anhui University Hefei230039 China

Event Extraction involves extracting event-related information such as event types and event arguments from context, which has long been tackled through well-designed neural networks or fine-tuned pre-trained language models. These approaches require substantial annotated data for tuning parameters and are resource-intensive. Recently, Prompting strategies with frozen parameters, such as Chain-of-Thought and Self-Consistency, have delivered success in NLP using LLMs by generating intermediate thought steps. However, they suffer from the challenge of error propagation and lack of interaction between different thoughts. In this paper, we propose Neural Network-based Prompting (NetPrompt), a novel network-structured prompting strategy for event extraction. The core idea behind NetPrompt is to imitate the excellent information integration capabilities of neural network structures. Specifically, we first decompose the event extraction problem into diverse intermediate subtasks, and each subtask is represented as a node in different layers of the network, the output of the nodes in the preceding layer is fed into the subsequent layer. Secondly, we propose pruning strategies to adapt the reasoning overhead to different problems. Finally, we have conducted extensive experiments on two widely used event extraction benchmarks to evaluate NetPrompt. The results demonstrated that NetPrompt significantly improved the event extraction performance compared to previous methods. ©2015 IEEE.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

Research on Image Description Generation Method Based on G-AoANet 5

Research on Image Description Generation Method Based on G-A...

引用

5th International Conference on Artificial Intelligence and Pattern Recognition, AIPR 2022

作者： Qiao, Pingan Shen, Ruixue Li, Yuan Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing School of Computer Science and Technology Xi'an University of Posts and Telecommunications Xi'an710121 China

ISBN: (纸本)9781450396899

Most of the image description generation methods in the attention-based encoder-decoder framework extract local features from images. Despite the relatively high semantic level of local features, it still has two problems to be solved, one is object loss, where some important objects may be lost when generating image descriptions, and the other is prediction error, as an object may be identified in the wrong class. In this paper, a G-AoANet model is proposed to solve the above problems. The model uses an attention mechanism to combine global features with local features. In this way, our model can selectively focus on both object and contextual information, improving the quality of the generated descriptions. Experimental results show that the model improves the initially reported best CIDEr-D and SPICE scores on the MS COCO dataset by 9.3% and 5.1% respectively. © 2022 ACM.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

A Novel Compact On-Chip Millimeter-Wave Band-Pass Filter with GaAs pHEMT Technology 13

A Novel Compact On-Chip Millimeter-Wave Band-Pass Filter wit...

引用

13th International Conference on Microwave and Millimeter Wave Technology, ICMMT 2021

作者： Wang, Wen-Tao Zhu, Hao-Ran Sun, Yu-Fa Huang, Zhi-Xiang Wu, Xian-Liang Anhui University Key Laboratory Of Intelligent Computing And Signal Processing Ministry Of Education Hefei230039 China

ISBN: (纸本)9781665434379

In this paper, a compact and high selectivity millimeter wave on-chip band-pass filter using GaAs pHEMT technology is proposed. A compact lumped element unit, which consists of a series LC resonator and an extra capacitor, is used to produce a transmission zero near the pass-band without occupying much area. The proposed filter consists two of the proposed resonators. An additional series resonator is grounded to produce a transmission zero. The area of the proposed filter is only 0.816×0.607mm2. The presented filter is worked on 25.5 GHz, the 3-dB bandwidth is 21.5 GHz to 29.5GHz. The insertion loss is around 1.1dB, and the return loss is better than 17dB. © 2021 IEEE.

关键词： Bandpass filters

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：