检索结果-内蒙古大学图书馆

14th International Conference on Knowledge Science, Engineering, and Management (KSEM)

作者： Feng, Linhui Qiao, Linbo Han, Yi Kan, Zhigang Gao, Yifu Li, Dongsheng Natl Univ Def Technol Natl Key Lab Parallel & Distributed Proc Changsha Peoples R China

ISBN: (纸本)9783030821470;9783030821463

Few-shot learning event extraction methods gain more and more attention due to their ability to handle new event types. Current few-shot learning studies mainly focus on English event detection, which suffering from error propagation due to the identify-then-classify paradigm. And these methods could not be applied to Chinese event extraction directly, because they suffer from the Chinese word-trigger mismatch problem. In this work, we explore the Chinese event extraction with limited labeled data and reformulate it as a few-shot sequence tagging task. To this end, we propose a novel and practical few-shot syntactic enhanced projection network (SEPN), which exploits a syntactic learner to not only integrate the semantics of the characters and the words by Graph Convolution Networks, but also make the extracted feature more discriminative through a cross attention mechanism. Differing from prototypical networks which may lead to poor performance due to the prototype of each class could be closely distributed in the embedding space, SEPN learns to project embedding to space where different labels are well-separated. Furthermore, we deliberately construct an adaptive max-margin loss to obtain efficient and robust prototype representation. Numerical experiments conducted on the ACE-2005 dataset demonstrate the efficacy of the proposed few-shot Chinese event extraction.

关键词： Few-shot learning Chinese event extraction Syntactic embedding Conditional Random Field Robust loss

来源：评论

学校读者我要写书评

暂无评论

A Framework of Data Augmentation While Active Learning for Chinese Named Entity Recognition 14th

A Framework of Data Augmentation While Active Learning for C...

引用

14th International Conference on Knowledge Science, Engineering, and Management (KSEM)

作者： Li, Qingqing Huang, Zhen Dou, Yong Zhang, Ziwen Natl Univ Def Technol Natl Key Lab Parallel & Distributed Proc Changsha Peoples R China

ISBN: (纸本)9783030821470;9783030821463

Named entity recognition (NER) is a basic task to construct knowledge graph. The training performance is limited with few labelled data. One solution is active learning, which can achieve ideal results by multi-round sampling strategy to augment unlabelled data. However, there is very few labelled data in the early rounds, which leads to slow improvement on training performance. We thus propose a framework of data augmentation while active learning. To validate our claims, we focus on Chinese NER task and carry out extensive experiments on two public datasets. Experimental results show that our framework is effective for a series of classical query strategy. We can achieve 99% of the best deep model trained on full data using only 22% of the data on Resume, 63% labelled data is reduced as compared to pure active learning (PAL).

关键词： Active learning Data augmentation Chinese NER Deep learning Query strategy

来源：评论

学校读者我要写书评

暂无评论

Verification of C programs using slicing execution

Verification of C programs using slicing execution

引用

5th International Conference on Quality Software (QSIC 2005)

作者： Yi, XD Wang, J Yang, XJ Natl Lab Parallel & Distributed Proc Changsha Peoples R China

ISBN: (纸本)0769524729

The paper presents a novel method, namely slicing execution, to verify C programs with respect to temporal safety properties. The distinguished feature is that it only simulates the execution of the relevant statements under abstraction criteria and checks the properties on the fly. The abstraction criterion begins with a proper initial set Of program variables and may be iteratively refined according to spurious counter-examples. Provided that the properties to be verified usually involve only a few variables in practical programs, slicing execution may have the same precision as path-sensitive simulation with the cost close to standard flow-sensitive dataflow analysis. The presented method has been used to verify the initial handshake process of SSL protocol based on the C source code of openssl-0.9.6c. The experiment results confirm our claim and show that slicing execution is not only practical but also effective.

关键词： C (programming language)

来源：评论

学校读者我要写书评

暂无评论

Automated Data Augmentation for Audio Classification

引用

IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE procESSING 2024年 32卷 2716-2728页

作者： Sun, Yanjie Xu, Kele Liu, Chaorun Dou, Yong Wang, Huaimin Ding, Bo Pan, Qinghua Natl Univ Def Technol Natl Key Lab Parallel & Distributed Proc Changsha 410073 Peoples R China iFlytek Co Ltd Hefei 230088 Peoples R China

Audio classification is a challenging task that requires categorizing audio data based on its content or characteristics. Existing approaches for audio classification rely either on supervised learning or fine-tuning based on self-supervised learning, both of which require manually labeled data. However, manually labeling audio datasets is a time-consuming and expensive process that limits the dataset's size. Moreover, the diversity of sound categories and class imbalances can further impede classification performance. To overcome these challenges, researchers have proposed various audio data augmentation methods. However, most of these methods focus less on augmentations combination and design and rely solely on waveform-based or spectrogram-based approaches. This paper presents an Automated Audio Augmentation (AAA) method for audio classification, which generates learnable and composable augmentation policies suitable for the audio classification task and can be employed in a plug-and-play manner. This method leverages both waveform-level and spectrogram-level augmentation, and a Bayesian optimization algorithm is proposed to search for composed augmentation policies. To the best of our knowledge, this is the first attempt to propose an automatic data augmentation method for audio classification tasks. Through large-scale empirical studies, we demonstrate that the proposed method outperforms previous competitive methods by a significant margin. We improve the average performance of multiple datasets by 6.421% and by 7.330% on few-shot scenarios, respectively.

关键词： Audio classification automated augmentation audio data augmentation

来源：评论

学校读者我要写书评

暂无评论

FPGA accelerator for protein secondary structure prediction based on the GOR algorithm

引用

BMC BIOINFORMATICS 2011年第Sup1期12卷 1-9页

作者： Xia, Fei Dou, Yong Lei, Guoqing Tan, Yusong Natl Univ Def Technol Natl Lab Parallel & Distributed Proc Dept Comp Sci Changsha 410073 Hunan Peoples R China

Background: Protein is an important molecule that performs a wide range of functions in biological systems. Recently, the protein folding attracts much more attention since the function of protein can be generally derived from its molecular structure. The GOR algorithm is one of the most successful computational methods and has been widely used as an efficient analysis tool to predict secondary structure from protein sequence. However, the execution time is still intolerable with the steep growth in protein database. Recently, FPGA chips have emerged as one promising application accelerator to accelerate bioinformatics algorithms by exploiting fine-grained custom design. Results: In this paper, we propose a complete fine-grained parallel hardware implementation on FPGA to accelerate the GOR-IV package for 2D protein structure prediction. To improve computing efficiency, we partition the parameter table into small segments and access them in parallel. We aggressively exploit data reuse schemes to minimize the need for loading data from external memory. The whole computation structure is carefully pipelined to overlap the sequence loading, computing and back-writing operations as much as possible. We implemented a complete GOR desktop system based on an FPGA chip XC5VLX330. Conclusions: The experimental results show a speedup factor of more than 430x over the original GOR-IV version and 110x speedup over the optimized version with multi-thread SIMD implementation running on a PC platform with AMD Phenom 9650 Quad CPU for 2D protein structure prediction. However, the power consumption is only about 30% of that of current general-propose CPUs.

关键词： Average Power Consumption FPGA Chip Final Prediction Result External DRAM Input Protein Sequence

来源：评论

学校读者我要写书评

暂无评论

Multi-level Shared Knowledge Guided Learning for Knowledge Graph Completion

TRANSACTIONS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTIC...

引用

TRANSACTIONS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS 2024年 12卷 1027-1042页

作者： Shan, Yongxue Zhou, Jie Peng, Jie Zhou, Xin Yin, Jiaqian Wang, Xiaodong Natl Univ Def Technol Coll Comp Natl Key Lab Parallel & Distributed Comp Changsha Peoples R China

In the task of Knowledge Graph Completion (KGC), the existing datasets and their inherent subtasks carry a wealth of shared knowledge that can be utilized to enhance the representation of knowledge triplets and overall performance. However, no current studies specifically address the shared knowledge within KGC. To bridge this gap, we introduce a multi-level Shared Knowledge Guided learning method (SKG) that operates at both the dataset and task levels. On the dataset level, SKG-KGC broadens the original dataset by identifying shared features within entity sets via text summarization. On the task level, for the three typical KGC subtasks-head entity prediction, relation prediction, and tail entity prediction-we present an innovative multi-task learning architecture with dynamically adjusted loss weights. This approach allows the model to focus on more challenging and underperforming tasks, effectively mitigating the imbalance of knowledge sharing among subtasks. Experimental results demonstrate that SKG-KGC outperforms existing text-based methods significantly on three well-known datasets, with the most notable improvement on WN18RR (MRR: 66.6%-> 72.2%, Hit@1: 58.7%-> 67.0%).

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Deriving software statistical testing model from UML model 3

Deriving software statistical testing model from UML model

引用

3rd International Conference on Quality Software

作者： Yan, J Wang, J Chen, HW Natl Lab Parallel & Distributed Proc Changsha Peoples R China

ISBN: (纸本)0769520154

Software statistical testing is concerned with testing the entire software systems based on their usage models. In the context of UML-based development, it is desired that usage models can be derived from UML analysis artifacts. This paper presents a method that derives the software usage models from reasonably constrained UML artifacts. The method utilizes use case diagrams, sequence diagrams and the execution probability of each sequence diagram in its associated use case. By projecting the messages in sequence diagrams onto the objects under test, the method elicits messages and their occurrence probabilities for generating the usage model of each use case for the objects under test. Then the usage models of use cases are integrated into the system usage model. The integration procedure will utilize the execution sequential relations between use cases.

关键词： sequence diagram UML Statistical tests Messages Legal Executions Software systems computer software computer programs

来源：评论

学校读者我要写书评

暂无评论

Revised stride data value predictor design

Revised stride data value predictor design

引用

8th International Conference on High-Performance Computing in Asia-Pacific Region

作者： Xiao Yong Yang Yanping Zhou Xingming Natl Lab Parallel & Distributed Proc Changsha Peoples R China

ISBN: (纸本)0769524869

Stride data value predictor is widely used by researchers in data value prediction study. Compared with context-based hybrid data value predictors, stride data value predictors are simple. But when encountering non-stride repeated sequences, a stride value predictor does not perform as well as a context-based hybrid data value predictor. In this paper, a revised stride data value predictor is introduced With a little augment to a traditional stride data value predictor, the new predictor can make correct predictions on some patterns that can only be done by the context-based data value predictors. Simulation results show that the new predictor works well with most value predictable instructions. Design decisions such as predictor size, confidence mechanism and storing partial tag are analyzed.

关键词： Data acquisition

来源：评论

学校读者我要写书评

暂无评论

CPU-GPU hybrid parallel strategy for cosmological simulations

引用

CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE 2014年第3期26卷 748-765页

作者： Wang, Yueqing Dou, Yong Guo, Song Lei, Yuanwu Zou, Dan Natl Univ Def Technol Natl Lab Parallel & Distributed Proc Dept Comp Sci Changsha 410073 Hunan Peoples R China

Gadget is a simulation application for N-body and smoothed particle hydrodynamics problems in cosmology, and it is widely applied in solving series of cosmological problems. N-body focuses on the motion of the interaction of N particles, and smoothed particle hydrodynamics is a fluid simulation algorithm that studies the movement of fluid through particle simulation. Most scholars focus their attention on accelerating Gadget on multi-core CPU or graphics processing units (GPUs) platforms. However, these research activities failed to achieve CPU-GPU hybrid computing, which resulted in tremendous waste of CPU computing *** this paper, we propose a CPU-GPU hybrid parallel strategy to accelerate Gadget-2, a massively parallel structure formation code for cosmological simulations. This strategy uses CPU and GPU to process the calculation of short-range force. To ensure CPU and GPU workload balance, a dynamic task allocation scheme is proposed according to the computational performance difference between the CPU and *** results showed that our CPU-GPU hybrid parallel strategy achieved an overall speedup factor of 18.6 and a partial speedup factor for short-range force calculation of 28.35 compared with a single-core CPU implementation for particles in million-size magnitudes. Moreover, compared with a GPU platform that contained 12 CPU cores and one GPU, our hybrid parallel strategy obtained overall speedup and partial speedup factors of 6% and 20%, respectively. Furthermore, the scalability of the hybrid strategy is very fine - its performance will be enhanced when the problem scale is increasing. However, this strategy also has its limitation that the performance enhancement will be decreasing if the ratio(the number of CPU cores divides that of the GPU cards) reduces. Finally, in our hybrid strategy, the CPU coefficient of utilization improved by 17.14% or better. Copyright (c) 2013 John Wiley & Sons, Ltd.

关键词： cosmological hybrid parallel accelerate

来源：评论

学校读者我要写书评

暂无评论

HybridNN: An accurate and scalable network location service based on the inframetric model

引用

FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE 2013年第6期29卷 1485-1504页

作者： Fu, Yongquan Wang, Yijie Biersack, Ernst Natl Univ Def Technol Coll Comp Sci Natl Key Lab Parallel & Distributed Proc Changsha 410073 Hunan Peoples R China EURECOM Sophia Antipolis France

Locating servers that have shortest interactive delay towards an Internet host provides an important service for large-scale latency sensitive networked applications, such as VoIP, online network games, or interactive network services on the cloud. Existing algorithms assume that the delay space is a metric space, which implies that the delay between two nodes is symmetric and the triangle inequality holds. In practice, the delay space is not metric, which lowers the accuracy of metric-based algorithms. We develop a new scheme whose theoretical foundation is based on the inframetric model, which has weaker assumptions than the metric model. We prove that the location requests can be completed efficiently if the delay space exhibits modest inframetric dimensions, which we can confirm empirically. Finally, we propose HybridNN (Hybrid Nearest Service Node Location) that finds the closest service node accurately thanks to the inframetric model and scalably by combining delay predictions with direct probes to a pruned set of neighbors. Simulation results show that HybridNN locates in nearly all cases the true nearest service nodes. Experiments on Planetlab show that with modest query overhead and maintenance traffic HybridNN can provide accurate nearest service nodes that are close to optimal. (C) 2012 Elsevier B.V. All rights reserved.

关键词： distributed nearest server location Peer-to-Peer Inframetric Growth dimension

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：