检索结果-内蒙古大学图书馆

26th International Conference on Computational Linguistics, COLING 2016

作者： Li, Wei He, Lei Zhuge, Hai Key Lab. of Intelligent Information Processing Institute of Computing Technology University of Chinese Academy of Sciences Beijing China Aston University Birmingham United Kingdom

ISBN: (纸本)9784879747020

This paper studies the abstractive multi-document summarization for event-oriented news texts through event information extraction and abstract representation. Fine-grained event mentions and semantic relations between them are extracted to build a unified and connected event semantic link network, an abstract representation of source texts. A network reduction algorithm is proposed to summarize the most salient and coherent event information. New sentences with good linguistic quality are automatically generated and selected through sentences over-generation and greedy-selection processes. Experimental results on DUC 2006 and DUC 2007 datasets show that our system significantly outperforms the state-of-the-art extractive and abstractive baselines under both pyramid and ROUGE evaluation metrics. © 1963-2018 ACL.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

ICT: A system combination for Chinese semantic dependency parsing 1

ICT: A system combination for Chinese semantic dependency pa...

引用

1st Joint Conference on Lexical and Computational Semantics, *SEM 2012

作者： Xiong, Hao Liu, Qun Key Lab. of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences P.O. Box 2704 Beijing100190 China

ISBN: (纸本)9781937284220

The goal of semantic dependency parsing is to build dependency structure and lab.l semantic relation between a head and its modifier. To attain this goal, we concentrate on obtaining better dependency structure to predict better semantic relations, and propose a method to combine the results of three state-of-The-Art dependency parsers. Unfortunately, we made a mistake when we generate the final output that results in a lower score of 56.31%in term of lab.led Attachment Score (LAS), reported by organizers. After giving golden testing set, we fix the bug and rerun the evaluation script, this time we obtain the score of 62.8% which is consistentwith the results on developing set. We will report detailed experimental results with correct program as a comparison standard for further research. © 2012 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

Automatic adaptation of annotation standards for dependency parsing - Using projected treebank as source corpus 11

Automatic adaptation of annotation standards for dependency ...

引用

11th International Conference on Parsing Technologies, IWPT 2009

作者： Jiang, Wenbin Liu, Qun Key Lab. of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences P.O. Box 2704 Beijing100190 China

We describe for dependency parsing an annotation adaptation strategy, which can automatically transfer the knowledge from a source corpus with a different annotation standard to the desired target parser, with the supervision by a target corpus annotated in the desired standard. Furthermore, instead of a hand-annotated one, a projected treebank derived from a bilingual corpus is used as the source corpus. This benefits the resource-scarce languages which haven't different hand-annotated treebanks. Experiments show that the target parser gains significant improvement over the baseline parser trained on the target corpus only, when the target corpus is smaller. © 2009 Association for Computational Linguistics

关键词： Forestry

来源：评论

学校读者我要写书评

暂无评论

ICT: A translation based method for cross-lingual textual entailment 1

ICT: A translation based method for cross-lingual textual en...

引用

1st Joint Conference on Lexical and Computational Semantics, *SEM 2012

作者： Meng, Fandong Xiong, Hao Liu, Qun Key Lab. of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences P.O. Box 2704 Beijing100190 China

ISBN: (纸本)9781937284220

In this paper, we present our system description in task of Cross-lingual Textual Entailment. The goal of this task is to detect entailment relations between two sentences written in different languages. To accomplish this goal, we first translate sentences written in foreign languages into English. Then, we use EDITS1, an open source package, to recognize entailment relations. Since EDITS only draws monodirectional relations while the task requires bidirectional prediction, thus we exchange the hypothesis and test to detect entailment in another direction. Experimental results show that our method achieves promising results but not perfect results compared to other participants. © 2012 Association for Computational Linguistics.

关键词： Translation (languages)

来源：评论

学校读者我要写书评

暂无评论

A Diversity Based Competitive Multi-objective PSO for Feature Selection 1

引用

15th International Conference on intelligent computing, ICIC 2019

作者： Qiu, Jianfeng Cheng, Fan Zhang, Lei Xu, Yi School of Computer Science and Technology Anhui University Hefei230039 China Key Lab of Intelligent Computing and Signal Processing of Ministry of Education Anhui University Hefei230039 China

ISBN: (数字)9783030269692

ISBN: (纸本)9783030269685

Multi-Objective Particle Swarm Optimization (MOPSO) for feature selection has attracted increasing attention of researchers recently. However, in the existing methods, quick convergence usually degrades the diversity of the population, especially when many irrelevant and redundant features involved in them. To this end, a diversity based competitive multi-objective particle swarm optimization for feature selection problem (named D-CMOPSO) is proposed. In D-CMOPSO, a diversified competition based learning mechanism is proposed to improve the quality of found feature subset, which consists of three parts: exemplar particle construction, pairwise competition, and diversified learning strategy. The proposed competition mechanism utilizes the above three parts to boost the diversity in the following generations. Moreover, in order to guide the initial population to evolve the promising area, a maximal information coefficient based initialization strategy is also suggested. The experimental results demonstrate that the proposed D-CMOPSO is competitive for feature selection problem. © 2019, Springer Nature Switzerland AG.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

An efficient implementation of double precision 1-D FFT for GPUs Using CUDA

引用

Journal of Information and Computational Science 2012年第2期9卷 387-394页

作者： Liu, Yanjun Guo, Licai Luo, Bin Zhang, Xingyi School of Computer Science and Technology Anhui University Hefei 230039 China Key Lab of Intelligent Computing and Signal Processing of Ministry of Education Anhui University Hefei 230039 China School of Computer Science and Technology University of Science and Technology of China Hefei 230027 China

Fast Fourier Transform (FFT) is a well known and widely used tool in many scientific and engineering fields. CUFFT, which is the NVIDIA's FFT library included in the CUDA toolkit, supports double precision FFTs. However, the implementation of CUFFT is not very efficient. In this paper, we implement an efficient double-precision Cooley-tukey algorithm for GPUs using CUDA. Some programming techniques are employed to exploit the hardware characteristics. These techniques include on-chip shared memory utilization, removing redundant computation, and coalescing the global memory access. Experiments show that the performance of our 1-D FFT is as fast as CUFFT. Furthermore, the performance of our FFT implementation is more than twice faster than CUFFT for small input sizes. Copyright © 2012 Binary Information Press.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

引用

50th Annual Meeting of the Association for Computational Linguistics, ACL 2012

作者： Xiao, Xinyan Xiong, Deyi Zhang, Min Liu, Qun Lin, Shouxun Key Lab. of Intelligent Info. Processing Chinese Academy of Sciences Institute of Computing Technology China Human Language Technology Institute for Infocomm Research Singapore

ISBN: (纸本)9781937284244

Previous work using topic model for statistical machine translation (SMT) explore topic information at the word level. However, SMT has been advanced from word-based paradigm to phrase/rule-based paradigm. We therefore propose a topic similarity model to exploit topic information at the synchronous rule level for hierarchical phrase-based translation. We associate each synchronous rule with a topic distribution, and select desirable rules according to the similarity of their topic distributions with given documents. We show that our model significantly improves the translation performance over the baseline on NIST Chinese-to-English translation experiments. Our model also achieves a better performance and a faster speed than previous approaches that work at the word level. © 2012 Association for Computational Linguistics.

关键词： Machine translation

来源：评论

学校读者我要写书评

暂无评论

Research on automatic construction of the dynamic Chinese porn feature knowledge system

Research on automatic construction of the dynamic Chinese po...

引用

2010 International Conference on Computer Design and Applications, ICCDA 2010

作者： Peno, Yu-Zhong Yuan, Chang-An Qin, Xiao Key Lab. of Scientific Computing and Intelligent Information Processing in Universities of Guangxi School of Computer and Information Engineering Guangxi Teacher Education University Nanning 530001 China

ISBN: (纸本)9781424471638

As the Web continues to grow, the pornographic texts in varied forms run rampant on Internet, despite repeated prohibitionsm. It severely does harms to the development of people's mental health and the stability of sociality. In this paper, We propose a novel and effective feature weight-value calculating method named FEFP for such objectionable information, and design a scheme to auto-build system of porn feature knowledge which can be dynamically updated. The experiments are designed and conducted to compare the FEFP with four famous existing methods of Web page feature extraction. Experimental results show that the proposed approach has both higher feature coverage and lower redundancy rates for either porn on conventional forms or porn whose form has been changed. It is very good and very suitable for processing the harmful information in current form which is volatile and increasingly hidden. © 2010 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

A computing model for concept fusing and document classification

A computing model for concept fusing and document classifica...

引用

2006 2nd International Conference on Semantics Knowledge and Grid, SKG

作者： Zhang, Nan He, Chao Key Lab. of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences P.O.Box 2704-28 100080 Beijing China

ISBN: (纸本)0769532055

Effective document classification is a long-pursued goal in knowledge management. This paper proposes a novel hybrid approach of semantic representation and statistical measurements. Document is divided into content segments first. By Formal Concept Analysis (FCA), their semantic links with standard concept identifiers are built up whose weights are calculated statistically. In this way, effective concept fusing and document classification can be achieved. In addition, a semantic overlay for specific documents will be constructed via concept fusing. Experiments show our approach is feasible and effective. © 2006 IEEE.

关键词： Formal concept analysis

来源：评论

学校读者我要写书评

暂无评论

The SP-FDTD method for High-Order FDTD Plane Wave Injection

The SP-FDTD method for High-Order FDTD Plane Wave Injection

引用

第九届国际天线、电波传播及电磁理论学术研讨会(ISAPE2010)

作者： Lei Wu Zhi-xiang Huang Hui Wang Jia-xun Sun Xin-gang Ren Xian-liang Wu Key Lab of Intelligent Computing & Signal Processing Anhui University Ministry of Education Hefei Key Lab of Intelligent Computing & Signal Processing Anhui University Ministry of Education Hefei

In the paper, the method of splitting plane wave FDTD (SP-FDTD) algorithm, an efficient method of introducing plane wave source into finite difference time domain grids, is presented for solving oblique incident wave for the modified high-order FDTD (M24 scheme). Numerical examples in 2-D demonstrate the valid of the method and normalized field leakage was measured at -320 dB levels.

关键词： Time domain analysis Finite difference methods Antennas

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：