检索结果-内蒙古大学图书馆

2nd Conference on Machine Translation, WMT 2017

作者： Zhang, Jinchao Porkaew, Peerachet Hu, Jiawei Zhao, Qiuye Liu, Qun Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China ADAPT Centre School of Computing Dublin City University Ireland

ISBN: (纸本)9781945626968

We participated in the WMT 2016 shared news translation task on English ? Chinese language pair. Our systems are based on the encoder-decoder neural machine translation model with the attention mechanism. We employ the Gated Recurrent Unit (GRU) with the linear associative connection to build deep encoder and address the unknown words with the dictionary replace approach. The dictionaries are extracted from the parallel training data with unsupervised word alignment method. In the decoding procedure, the translation probabilities of the target word from different models are averagely combined as the ensemble strategy. In this paper, we introduce our systems from data preprocessing to post-editing in details. © 2017 Association for Computational Linguistics

关键词： Neural machine translation

来源：评论

学校读者我要写书评

暂无评论

The correspondence between the concepts in description logics for contexts and formal concept analysis

引用

Science China(information Sciences) 2012年第5期55卷 1106-1122页

作者： MA Yue 1,2,SUI YueFei 1 & CAO CunGen 1 1 key laboratory of intelligent information processing,Institute of computing Technology,Chinese Academy of Sciences,Beijing 100190,China 2 Graduate University of Chinese Academy of Sciences,Beijing,China 1. Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing 100190 China2. Graduate University of Chinese Academy of Sciences Beijing 100049 China

Formal concept analysis (FCA) and description logic (DL) are meant to be formalizations of concepts.A formal concept in the former consists of its intent and extent,where the intent is the set of all the attributes shared by each object in the extent of the concept,and the extent is the set of all the objects sharing each property in the intent of the concept.A concept in the latter formalization is simply a concept name,the interpretation of which is a subset of a *** consider the correspondence between concepts in both formalizations,a multi-valued formal context must be represented both as a knowledge base and as a model of the DL for contexts,where concepts are decomposed into tuple concepts C,interpreted as a set of tuples and value concepts V,interpreted as a set of attribute-value *** show that there is a difference between the interpretation of concepts R.V /R.C and the Galois connection between the extent/intent of formal concepts in *** to the Galois connection,there should be concepts of the form + R.V and + R.C inter-preted in FCA,and hence the logical language L for DL is extended to be L + together with + as a constructor so that + R.V and + R.C are well-defined ***,according to the interpretation in DL there should be pseudo concepts in FCA so that the interpretation of concepts R.V /R.C is the extent/intent of pseudo *** correspondence between formal concepts and concepts in L +,and between pseudo concepts and concepts in L are presented in this paper.

关键词： description logic formal concept analysis concept attribute/role

来源：评论

学校读者我要写书评

暂无评论

An automatic semantic relationships discovery approach 04

An automatic semantic relationships discovery approach

引用

13th International World Wide Web Conference on Alternate Track, Papers and Posters, WWW Alt. 2004

作者： Zhuge, Hai Zheng, Liping Zhang, Nan Li, Xiang China Knowledge Grid Research Group Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China

ISBN: (纸本)1581139128

An important obstacle to the success of the Semantic Web is that the establishment of the semantic relationship is labor-intensive. This paper proposes an automatic semantic relationship discovering approach for constructing the semantic link network. The basic premise of this work is that the semantics of a web page can be reflected by a set of keywords, and the semantic relationship between two web pages can be determined by the semantic relationship between their keyword sets. The approach adopts the data mining algorithms to discover the semantic relationships between keyword sets, and then uses deductive and analogical reasoning to enrich the semantic relationships. The proposed algorithms have been implemented. Experiment shows that the approach is feasible.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

A subtree-based factorization of dependency parsing 26

A subtree-based factorization of dependency parsing

引用

26th International Conference on Computational Linguistics, COLING 2016

作者： Zhao, Qiuye Liu, Qun Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China ADAPT Centre School of Computing Dublin City University Ireland

ISBN: (纸本)9784879747020

We propose a dependency parsing pipeline, in which the parsing of long-distance projections and localized dependencies are explicitly decomposed at the input level. A chosen baseline dependency parsing model performs only on 'carved' sequences at the second stage, which are transformed from coarse constituent parsing outputs at the first stage. When k-best constituent parsing outputs are kept, a third-stage is required to search for an optimal combination of the overlapped dependency subtrees. In this sense, our dependency model is subtree-factored. We explore alternative approaches for scoring subtrees, including feature-based models as well as continuous representations. The search for optimal subset to combine is formulated as an ILP problem. This framework especially benefits the models poor on long sentences, generally improving baselines by 0.75-1.28 (UAS) on English, achieving comparable performance with high-order models but faster. For Chinese, the most notable increase is as high as 3.63 (UAS) when the proposed framework is applied to first-order parsing models. © 1963-2018 ACL.

关键词： Syntactics

来源：评论

学校读者我要写书评

暂无评论

Enhancing Multi-turn Dialogue Modeling with Intent information for E-Commerce Customer Service 9th

Enhancing Multi-turn Dialogue Modeling with Intent Informati...

引用

9th CCF International Conference on Natural Language processing and Chinese computing, NLPCC 2020

作者： Liu, Ruixue Chen, Meng Liu, Hang Shen, Lei Song, Yang He, Xiaodong JD AI Beijing China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China

ISBN: (纸本)9783030604493

Nowadays, it is a heated topic for many industries to build intelligent conversational bots for customer service. A critical solution to these dialogue systems is to understand the diverse and changing intents of customers accurately. However, few studies have focused on the intent information due to the lack of large-scale dialogue corpus with intent labelled. In this paper, we propose to leverage intent information to enhance multi-turn dialogue modeling. First, we construct a large-scale Chinese multi-turn E-commerce conversation corpus with intent labelled, namely E-IntentConv, which covers 289 fine-grained intents in after-sales domain. Specifically, we utilize the attention mechanism to extract Intent Description Words (IDW) for representing each intent explicitly. Then, based on E-IntentConv, we propose to integrate intent information for both retrieval-based model and generation-based model to verify its effectiveness for multi-turn dialogue modeling. Experimental results show that extra intent information is useful for improving both response selection and generation tasks. © 2020, Springer Nature Switzerland AG.

关键词： Electronic commerce

来源：评论

学校读者我要写书评

暂无评论

Viterbi Decoding of Directed Acyclic Transformer for Non-Autoregressive Machine Translation

Viterbi Decoding of Directed Acyclic Transformer for Non-Aut...

引用

2022 Findings of the Association for Computational Linguistics: EMNLP 2022

作者： Shao, Chenze Ma, Zhengrui Feng, Yang Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China

Non-autoregressive models achieve significant decoding speedup in neural machine translation but lack the ability to capture sequential dependency. Directed Acyclic Transformer (DA-Transformer) was recently proposed to model sequential dependency with a directed acyclic graph. Consequently, it has to apply a sequential decision process at inference time, which harms the global translation accuracy. In this paper, we present a Viterbi decoding framework for DA-Transformer, which guarantees to find the joint optimal solution for the translation and decoding path under any length constraint. Experimental results demonstrate that our approach consistently improves the performance of DA-Transformer while maintaining a similar decoding speedup. © 2022 Association for Computational Linguistics.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

αSetup-PCTL:An Adaptive Setup-Based Two-Level Preconditioner for Sequence of Linear Systems of Three-Temperature Energy Equations

引用

Communications in Computational Physics 2022年第10期32卷 1287-1309页

作者： Silu Huang Xiaoqiang Yue Xiaowen Xu Laboratory of Computational Physics Institute of Applied Physics and ComputationalMathematicsBeijing 100088China National Center for Applied Mathematics in Hunan Key Laboratory of Intelligent Computing and Information Processing of Ministry of EducationHunan Key Laboratory for Computation and Simulation in Science and EngineeringXiangtan UniversityXiangtan 411105China

The iterative solution of the sequence of linear systems arising from threetemperature(3-T)energy equations is an essential component in the numerical simulation of radiative hydrodynamic(RHD)***,due to the complicated application features of the RHD problems,solving 3-T linear systems with classical preconditioned iterative techniques is *** address this difficulty,a physicalvariable based coarsening two-level(PCTL)preconditioner has been proposed by dividing the fully coupled system into four individual easier-to-solve *** its nearly optimal complexity and robustness,the PCTL algorithm suffers from poor efficiency because of the overhead associatedwith the construction of setup phase and the solution of ***,the PCTL algorithm employs a fixed strategy for solving the sequence of 3-T linear systems,which completely ignores the dynamically and slowly changing features of these linear *** address these problems and to efficiently solve the sequence of 3-T linear systems,we propose an adaptive two-level preconditioner based on the PCTL algorithm,referred to as α*** adaptive strategies of the αSetup-PCTL algorithm are inspired by those of αSetup-AMG algorithm,which is an adaptive-setup-based AMG solver for sequence of sparse linear *** proposed αSetup-PCTL algorithm could adaptively employ the appropriate strategies for each linear system,and thus increase the overall *** results demonstrate that,for 36 linear systems,the αSetup-PCTL algorithm achieves an average speedup of 2.2,and a maximum speedup of 4.2 when compared to the PCTL algorithm.

关键词： Sequence of linear systems sparse linear solver preconditioning methods radiation hydrodynamics simulation

来源：评论

学校读者我要写书评

暂无评论

Motion Matters: Difference-based Multi-scale Learning for Infrared UAV Detection

Motion Matters: Difference-based Multi-scale Learning for In...

引用

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2023

作者： He, Ruian Zhou, Shili Cheng, Ri Sun, Yuqi Tan, Weimin Yan, Bo Shanghai Collaborative Innovation Center of Intelligent Visual Computing Fudan University School of Computer Science Shanghai Key Laboratory of Intelligent Information Processing Shanghai China

ISBN: (纸本)9798350302493

Unmanned Aerial Vehicle (UAV) detection in the wild is a challenging task due to the presence of background noise and the varying size of the object. To address these obstacles, we propose a novel learning framework for robust UAV detectors, which we call Difference-based Multi-scale Learning (DML). We argue that motion information matters in UAV detection because of the low recognition in one frame. Our method utilizes the frame difference of multiple previous frames, extracting motion information and blocking background noise. We also fuse multiple spatial-temporal scales for training and inferencing, enabling fusion from different sources. In addition, to better evaluate the performance of UAV detection in different scales, we propose Multi-Scale Average Precision (MSAP) metric to aggregate the detection accuracy over multiple scales. Through extensive experiments, we demonstrate that our proposed approach improves the detection accuracy of baseline models. Notably, we achieve SOTA performance in the 3rd Anti-UAV Challenge, with 2nd place in Track 2 and 4th place in Track 1. © 2023 IEEE.

关键词： Antennas

来源：评论

学校读者我要写书评

暂无评论

MAGE: Multi-agent environment

MAGE: Multi-agent environment

引用

2003 International Conference on Computer Networks and Mobile computing, ICCNMC 2003

作者： Shi, Zhongzhi Zhang, Haijun Dong, Mingkai Zhao, Zhikung Sheng, Qiujian Jiang, Yuncheng Cheng, Yong Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences PO Box 2704 Beijing100080 China

ISBN: (纸本)0769520332

intelligent agent technology has been raised as the primary technology in the intelligent Internet and mobile computing. In this paper, MAGE (multi-agent environment) is introduced which is an environment for rapidly developing distributed, heterogeneous multi-agent systems. Agent model, agent architecture, MAGE platforms, comparison between MAGE and other multi-agent framework is presented in the paper. This paper illustrates two application systems, such as e-business, parallel Web spider. The MAGE is written in Java and is a powerful tool to construct multi-agent systems for Internet applications. © 2003 IEEE.

关键词： Computer architecture

来源：评论

学校读者我要写书评

暂无评论

intelligent science 1

引用

12th International Conference on Rough Sets, Fuzzy Sets, Data Mining and Granular computing, RSFDGrC 2009

作者： Shi, Zhongzhi Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Science Kexueyuan Nanlu #6 Beijing 100190 China

ISBN: (数字)9783642106460

ISBN: (纸本)3642106455

Intelligence Science is an interdisciplinary subject which dedicates to joint research on basic theory and technology of intelligence by brain science, cognitive science, artificial intelligence and others. Brain science explores the essence of brain, research on the principles and models of natural intelligence at molecular, cellular, and behavior levels. cognitive science studies human mental activities, such as perception, learning, memory, thinking, consciousness etc. Artificial intelligence attempts simulation, extension, and expansion of human intelligence using artificial methods and technologies. Researchers specialized in above three disciplines work together to explore new concepts, theories, and methodologies. If successful, it will create a brilliant future in 21st century. The paper will outline the framework of intelligence science and present its ten big challenges. Tolerance Granular Space Model (TGSM) will be discussed as one of helpful approaches. © 2009 Springer-Verlag Berlin Heidelberg.

关键词： Artificial intelligence

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：