检索结果-内蒙古大学图书馆

5th International Workshop on Spoken Language Translation, IWSLT 2008

作者： Liu, Yang He, Zhongjun Mi, Haitao Huang, Yun Feng, Yang Jiang, Wenbin Lu, Yajuan Liu, Qun Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences P.O. Box 2704 Beijing100190 China

This paper presents a description for the ICT systems involved in the IWSLT 2008 evaluation campaign. This year, we participated in Chinese-English and English-Chinese translation directions. Four statistical machine translation systems were used: one linguistically syntax-based, two formally syntax-based, and one phrase-based. The outputs of the four SMT systems were fed to a sentence-level system combiner, which was expected to produce better translations than single systems. We will report the results of the four single systems and the combiner on both the development and test sets. © 2008 International Workshop on Spoken Language Translation, IWSLT 2008. All rights reserved.

关键词： Syntactics

来源：评论

学校读者我要写书评

暂无评论

Variational neural discourse relation recognizer

Variational neural discourse relation recognizer

引用

2016 Conference on Empirical Methods in Natural Language processing, EMNLP 2016

作者： Zhang, Biao Xiong, Deyi Su, Jinsong Liu, Qun Ji, Rongrong Duan, Hong Zhang, Min Xiamen University Xiamen361005 China Provincial Key Laboratory for Computer Information Processing Technology Soochow University Suzhou215006 China ADAPT Centre School of Computing Dublin City University Ireland Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China

ISBN: (纸本)9781945626258

Implicit discourse relation recognition is a crucial component for automatic discourse-level analysis and nature language understanding. Previous studies exploit discriminative models that are built on either powerful manual features or deep discourse representations. In this paper, instead, we explore generative models and propose a variational neural discourse relation recognizer. We refer to this model as VarNDRR. VarNDRR establishes a directed probabilistic model with a latent continuous variable that generates both a discourse and the relation between the two arguments of the discourse. In order to perform efficient inference and learning, we introduce neural discourse relation models to approximate the prior and posterior distributions of the latent variable, and employ these approximated distributions to optimize a reparameterized variational lower bound. This allows VarNDRR to be trained with standard stochastic gradient methods. Experiments on the benchmark data set show that VarNDRR can achieve comparable results against state-of-the-art baselines without using any manual features. © 2016 Association for Computational Linguistics

关键词： Gradient methods

来源：评论

学校读者我要写书评

暂无评论

Reasoning theory for D3L with compositional bridge rules

Reasoning theory for D3L with compositional bridge rules

引用

7th IFIP International Conference on intelligent information processing, IIP 2012

作者： Zhao, Xiaofei Tian, Dongping Chen, Limin Shi, Zhongzhi Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China Research Institute of China Unicom Beijing China

ISBN: (纸本)9783642328909

The semantic mapping in Distributed Dynamic Description Logics (D3L) allows knowledge to propagate from one ontology to another. The current research for knowledge propagation in D3L is only for a simplified case when only two ontologies are involved. In this paper we study knowledge propagation in more complex cases. We find in the case when more than two ontologies are involved and bridge rules form chains, knowledge does not always propagate along chains of bridge rules even if we would expect it. Inspired by Package-based description Logics, we extend the original semantics of D3L by imposing so called compositional consistency condition on domain relations in D3L interpretations. Under this semantics knowledge propagates along chains of bridge rules correctly. Furthermore we provide a distributed Tableaux reasoning algorithm for deciding satisfiability of concepts which is decidable in D3L under compositional consistency. Compared with original one, the extended D3L provides more reasonable logic foundation for distributed, dynamic system such as the information integration system and the Semantic Web. © 2012 IFIP International Federation for information processing.

关键词： Ontology

来源：评论

学校读者我要写书评

暂无评论

Joint Decoding with Multiple Translation Models

Joint Decoding with Multiple Translation Models

引用

Joint Conference of the 47th Annual Meeting of the Association for Computational Linguistics and 4th International Joint Conference on Natural Language processing of the AFNLP, ACL-IJCNLP 2009

作者： Liu, Yang Mi, Haitao Feng, Yang Liu, Qun Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences P.O. Box 2704 Beijing100190 China

ISBN: (纸本)9781617382581

Current SMT systems usually decode with single translation models and cannot benefit from the strengths of other models in decoding phase. We instead propose joint decoding, a method that combines multiple translation models in one decoder. Our joint decoder draws connections among multiple models by integrating the translation hypergraphs they produce individually. Therefore, one model can share translations and even derivations with other models. Comparable to the state-of-the-art system combination technique, joint decoding achieves an absolute improvement of 1.5 BLEU points over individual decoding. © 2009 ACL and AFNLP.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

A visual awareness pathway in cognitive model ABGP

引用

High Technology Letters 2016年第4期22卷 395-403页

作者：马刚 Yang Xi Lu Chengxiang Zhang Bo Shi Zhongzhi The Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing 100190 P. R. China University of Chinese Academy of Sciences Beijing 100190 P. R. China

The cognitive model ABGP is a special model for agents,which consists of awareness,beliefs,goals and plans. The ABGP agents obtain the knowledge directly from the natural scenes only through some single preestablished rules like most agent architectures. Inspired by the biological visual cortex( V1) and the higher brain areas perceiving the visual feature,deep convolution neural networks( CNN) are introduced as a visual pathway into ABGP to build a novel visual awareness module. Then a rat-robot maze search simulation platform is constructed to validate that CNN can be used for the awareness module of ABGP. According to the simulation results,the rat-robot implemented by the ABGP with the CNN awareness module reaches the excellent performance of recognizing guideposts,which directly enhances the capability of the communication between the agent and the natural scenes and improves the ability to recognize the real world,which successfully demonstrates that an agent can independently plan its path in terms of the natural scenes.

关键词： ABGP visual cortex(V1) convolution neural networks(CNN) awareness visual pathway

来源：评论

学校读者我要写书评

暂无评论

Boundary Cue Guidance and Contextual Feature Mining for Glass Segmentation 48

Boundary Cue Guidance and Contextual Feature Mining for Glas...

引用

48th IEEE International Conference on Acoustics, Speech and Signal processing, ICASSP 2023

作者： Xiao, Qiquan Zhang, Yuan Li, Xuanya Hu, Kai Xiangtan University Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education Xiangtan411105 China Baidu Inc. Beijing100085 China

ISBN: (纸本)9781728163277

Glass is ubiquitous in the real world, and its perception has many applications, including robot navigation and drone tracking. However, due to the transparent property of glass, the interior of a glass area can be any surrounding scene or object, which brings challenges for computer vision. Inspired by the human senses, boundary cues are one of the crucial factors for people to judge the location of glass contours. Hence, we propose a boundary cue guidance and contextual feature mining network (BCNet) to accurately and efficiently segment glass. Specifically, we first design a multi-branch boundary extraction module (MBEM) for learning accurate boundary cues combined with multi-level encoded features. Second, we propose a boundary cue guidance module (BCGM), inject the boundary cues into the representation learning, and provide constraints with object structure semantics to guide feature extraction. Besides, we design a contextual feature mining module (CFMM) to dynamically capture the contextual information of different receptive fields for the detection of different sizes and shapes of the glass. Finally, extensive experiments on two benchmark glass datasets, GDD and GSD. The results demonstrate that our BCNet achieves state-of-the-art segmentation performance against existing methods. © 2023 IEEE.

关键词： Boundary cue guidance Contextual feature Convolutional neural network Glass segmentation

来源：评论

学校读者我要写书评

暂无评论

Learning lexicalized reordering models from reordering graphs

Learning lexicalized reordering models from reordering graph...

引用

48th Annual Meeting of the Association for Computational Linguistics, ACL 2010

作者： Su, Jinsong Liu, Yang Lü, Yajuan Mi, Haitao Liu, Qun Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences P.O. Box 2704 Beijing 100190 China

ISBN: (纸本)9781617388088

Lexicalized reordering models play a crucial role in phrase-based translation systems. They are usually learned from the word-aligned bilingual corpus by examining the reordering relations of adjacent phrases. Instead of just checking whether there is one phrase adjacent to a given phrase, we argue that it is important to take the number of adjacent phrases into account for better estimations of reordering models. We propose to use a structure named reordering graph, which represents all phrase segmentations of a sentence pair, to learn lexicalized reordering models efficiently. Experimental results on the NIST Chinese-English test sets show that our approach significantly outperforms the baseline method. © 2010 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

Augment dependency-to-string translation with fixed and floating structures 25

Augment dependency-to-string translation with fixed and floa...

引用

25th International Conference on Computational Linguistics, COLING 2014

作者： Xie, Jun Xu, Jinan Liu, Qun Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China School of Computer and Information Technology Beijing Jiaotong University China School of Computing Dublin City University Ireland

ISBN: (纸本)9781941643266

In this paper, we propose an augmented dependency-to-string model to combine the merits of both the head-dependents relations at handling long distance reordering and the fixed and floating structures at handling local reordering. For this purpose, we first compactly represent both the head-dependent relation and the fixed and floating structures into translation rules;second, in decoding we build "on-the-fly" new translation rules from the compact translation rules that can incorporate non-syntactic phrases into translations, thus alleviate the non-syntactic phrase coverage problem of dependency-to-string translation (Xie et al., 2011). Large-scale experiments on Chinese-to-English translation show that our augmented dependency-to-string model gains significant improvement of averaged +0.85 BLEU scores on three test sets over the dependencyto- string model.

关键词： Syntactics

来源：评论

学校读者我要写书评

暂无评论

SSD Real-Time Illegal Parking Detection Based on Contextual information Transmission

引用

Computers, Materials & Continua 2020年第1期62卷 293-307页

作者： Huanrong Tang Aoming Peng Dongming Zhang Tianming Liu Jianquan Ouyang Key Laboratory of Intelligent Computing and Information Processing Ministry of EducationCollege of Information EngineeringXiangtan UniversityXiangtan411105China National Computer Network Emergency Response Technical Team/Coordination Center of China Beijing100029China Department of Computer Science the University of GeorgiaAthensGeorgiaUSA

With the improvement of the national economic level,the number of vehicles is still increasing year by *** to the statistics of National Bureau of Statics,the number is approximately up to 327 million in China by the end of 2018,which makes urban traffic pressure continues to rise so that the negative impact of urban traffic order is *** parking-the common problem in the field of transportation security is urgent to be solved and traditional methods to address it are mainly based on ground loop and manual supervision,which may miss detection and cost much *** to the rapidly developing deep learning sweeping the world in recent years,object detection methods relying on background segmentation cannot meet the requirements of complex and various scenes on speed and ***,an improved Single Shot MultiBox Detector(SSD)based on deep learning is proposed in our study,we introduce attention mechanism by spatial transformer module which gives neural networks the ability to actively spatially transform feature maps and add contextual information transmission in specified ***,we found out the best connection layer in the detection model by repeated experiments especially for small objects and increased the precision by 1.5%than the baseline SSD without extra training ***,we designed an illegal parking vehicle detection method by the improved SSD,reaching a high precision up to 97.3%and achieving a speed of 40FPS,superior to most of vehicle detection methods,will make contributions to relieving the negative impact of illegal parking.

关键词： Contextual information transmission illegal parking detection spatial attention mechanism deep learning

来源：评论

学校读者我要写书评

暂无评论

A fixed-point decoding approach for statistical machine translation on mobile terminals

A fixed-point decoding approach for statistical machine tran...

引用

2010 4th International Universal Communication Symposium, IUCS 2010

作者： Li, Xiang Xu, Jin'an Jiang, Wenbin Liu, Qun Lü, Yajuan School of Computer and Information Technology Beijing Jiaotong University Beijing China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China

ISBN: (纸本)9781424478200

The demand for statistical machine translation on mobile terminals is increasing rapidly, but translation speed is restricted by the embedded processors without a floating-point unit. This paper proposes an approach to convert floating-point numbers into fixed-point numbers for SMT decoding on mobile terminals in order to reduce the impact of the processors without a floating-point unit on translation speed. The experiments based on PC and mobile terminal show that this approach ensures the quality of translation and the speed of fixed-point arithmetic operations is 135.6% faster than that of floating-point arithmetic operations. Therefore, this approach can efficiently improve translation speed of SMT systems on mobile terminals with weak ability in floating-point arithmetic operations. ©2010 IEEE.

关键词： Decoding

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：