检索结果-内蒙古大学图书馆

IEEE International Conference on Software Engineering and Service Sciences (ICSESS)

作者： Guoqiang Li Dandan Song Lejian Liao Fuzhen Sun Jianguang Du School of informatics Linyi University Linyi China Language Information Processing & Cloud Computing Applications Beijing Institute of Technology Beijing China Beijing Engineering Research Centre of High Volume Language Information Processing & Cloud Computing Applications School of Computer Science Beijing Institute of Technology Beijing China

ISBN: (纸本)9781479932801

Service-oriented computing is a widely adopted paradigm in real applications. Considering the continuous evolution of services, adaptive service composition has always been a major concern. It is a big challenge to adjust the composition to be optimal in real-time. In this paper, a learning automata-based approach is proposed to attack this problem. It consists of two important components: random environment and a learning automaton. The former can be mapped to the service's execution environment. The latter is responsible for the adaptation achievement using reward and penalty functions, while we take the service composition structures into account to compute the usefulness value of all services. At last, simulation study has shown that our approach is efficient to find the optimal (sub-optimal) composition.

关键词： Learning automata Quality of service Web services Adaptation models Automata Conferences Real-time systems

来源：评论

学校读者我要写书评

暂无评论

A parallel cross-language retrieval system for patent documents

A parallel cross-language retrieval system for patent docume...

引用

IEEE International Conference on Software Engineering and Service Sciences (ICSESS)

作者： Xin Shen Heyan Huang Lingzhi Li Yonggang Huang Beijing Engineering Research Center of High Volume Language Information Processing & Cloud Computing Application Beijing Institute of Technology Beijing China Overhaul Branch Beijing Electric Power Company Beijing China

ISBN: (纸本)9781479983544

In order to help people obtain useful information from patent documents in different languages. This paper proposes a cross-language retrieval system to search Chinese and English patent documents simultaneously. This system consists of query translation module, document retrieval module and user interaction module. Query translation module is used to translate query based on bilingual dictionaries. Document retrieval module consists of monolingual retrieval system using standard vector space model. In order to retrieve in highly parallel, we use the MapReduce model to calculate the similarity. User interaction module provides users with interactive mechanism used to improve the retrieval accuracy in the system. It contains two parts: the second translation and relevance feedback. The experimental results show that our system has good performance.

关键词： Patents Dictionaries Context Data processing Accuracy Machine learning algorithms

来源：评论

学校读者我要写书评

暂无评论

information exchange in public-culture service domain bason on CIEM 20

Information exchange in public-culture service domain bason ...

引用

2020 ACM Turing Celebration Conference - China, ACM TURC 2020

作者： Wang, Yashen Shi, Ge Zhang, Xi China Academy of Electronics and Information Technology of CETC Beijing China Beijing Eng. Res. Ctr. of High Vol. Language Information Processing and Cloud Computing Applications School of Computer Beijing Institute of Technology Beijing China School of Cyberspace Security Beijing University of Posts and Telecommunications Beijing China

ISBN: (纸本)9781450375344

This paper proposes a novel framework for information exchange in public-culture service domain, which leverages: (i) a widely available translation language (i.e., eXtensible Markup language (XML)), and (ii) a consistent implementation methodology framework provided for within the China information Exchange Model (CIEM). The evaluation about public-culture effectiveness measurement mission, demonstrates the efficiency of the proposed framework. © 2020 ACM.

关键词： XML

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Domain Assignment BaseC on Word-Gloss

引用

China Communications 2012年第3期9卷 19-27页

作者：朱朝勇黄河燕史树敏 School of Computer Science and Technology University of Science and Technology of China School of Computer Science and Technology Beijing Institute of Technology Beijing Engineering Research Center of High Volume Language Information Processing & Cloud Computing Applications Beijing Institute of Technology

This paper proposes a hierarchical word domain assignment algorithm to automatically build domain dictionaries from Machine-Readable Dictionary(MRD).The process for word domain assignment can be divided into three steps:1) Hierarchical structure constructing;2) Classifier training;3) Word domain *** with the traditional methods,the hierarchical word domain assignment algorithm enhances the accuracy of word domain assignment while reducing human efforts on collecting *** on WordNet 2.0 show that 62.53% of the first domain labels are matched with the WordNet Domains 3.0 by using gloss-based word domain assignment,and the performance can be further improved by utilizing the hierarchical relationships among the domain sets.

关键词： natural language processing domaindictionary hierarchical classification domain as-sigrmaent WordNet MRD

来源：评论

学校读者我要写书评

暂无评论

Approximating to the Real Translation Quality for Neural Machine Translation via Causal Motivated Methods

引用

ACM Transactions on Asian and Low-Resource language information processing 2023年第5期22卷 1-26页

作者： Xuewen Shi Heyan Huang Ping Jian Yi-Kun Tang School of Computer Science and Technology Beijing Institute of Technology Beijing Engineering Research Center of High Volume Language Information Processing and Cloud Computing Applications Haidian District Beijing China

It is hard to evaluate translations objectively and accurately, which limits the applications of machine translation. In this article, we assume that the above phenomenon is caused by noise interference during translation evaluation, and we handle the problem through a perspective of causal inference. We assume that the observable translation score is affected by the unobservable true translation quality and some noise simultaneously. If there is a variable that is related to the noise and independent to the true translation quality, the related noise can be eliminated by removing the effect of that variable from the observed score. Based on the above causality hypothesis, this article studies the length bias problem of beam search for neural machine translation (NMT) and the input related noise problem of translation quality estimation (QE). For the NMT length bias problem, we conduct the experiments on four typical NMT tasks (Uyghur–Chinese, Chinese–English, English–German, and English–French) with different scales of datasets. Comparing with previous approaches, the proposed causal motivated method is model-agnostic and does not require supervised training. For QE tasks, we conduct the experiments on the WMT’20 submissions. Experimental results show that the denoised QE results gain better Pearson’s correlation scores with human assessed scores compared to the original submissions. Further analyses on the NMT and QE tasks also demonstrate the rationality of the empirical assumptions made on our methods.

关键词： Neural machine translation causal inference half-sibling regression quality estimation

来源：评论

学校读者我要写书评

暂无评论

Combining CCG parsing and DL for Chinese question answering

引用

International Journal of Advancements in computing Technology 2012年第23期4卷 755-765页

作者： Li, Peng Liao, Lejian Wang, Liu Wang, Sheyang Beijing Engineering Research Centre High Volume Language Information Processing and Cloud Computing Applications School of Computer Science Beijing Institute of Technology Beijing 100081 China

This paper presents a novel Web Question Answering(WQA) approach based on the combination of Combinatory Categorial Grammar (CCG), Description Logic (DL) ontology and Web Service (WS), in order to promote semantic-level accuracy through deep text understanding and improve the solutions for non-WH questions. Our framework transforms a question answering problem into a service planning problem for which HTN planner-SHOP2 is used. It addresses transition from natural language to semantic expression and dynamical composition of web services via planning, and execution of the web services planning. We propose to take DL based semantic modeling, i.e., translating lambda-expression encoding of question meaning into DL based semantic representations. The advantage of such approach is a seamless exploitation of existing semantic resource coded as DL ontology, which is widespread in such areas as Semantic Web and conceptual modeling. The experiments are conducted with a repository of complex Chinese questions which involves the satisfaction of some object property restrictions. The experimental results show that producing the semantic representations with the combination of CCG parsing and DL reasoning is an effective approach for question understanding at semantic level, in terms of both understanding accuracy promotion and semantic resource exploitation.

关键词： Web services

来源：评论

学校读者我要写书评

暂无评论

Improving neural machine translation with sentence alignment learning

引用

Neurocomputing 2021年 420卷 15-26页

作者： Xuewen Shi Heyan Huang Ping Jian Yi-Kun Tang School of Computer Science and Technology Beijing Institute of Technology Beijing China Beijing Engineering Research Center of High Volume Language Information Processing and Cloud Computing Applications Beijing China

Neural machine translation (NMT) optimized by maximum likelihood estimation (MLE) usually lacks the guarantee of translation adequacy. To alleviate this problem, we propose an NMT approach that heightens the adequacy in machine translation by transferring the semantic knowledge from bilingual sentence alignment learning. Specifically, we first design a discriminator that learns to estimate sentence aligning score over translation candidates. The discriminator is constructed by gated self-attention based sentence encoders and trained with an N -pair loss for better capturing lexical evidences from bilingual sentence pairs. Then we propose an adversarial training framework as well as a sentence alignment-aware decoding method for NMT to transfer the discriminator’s learned semantic knowledge to NMT models. We conduct our experiments on Chinese → English, Uyghur → Chinese and English → German translation tasks. Experimental results show that our proposed methods outperform baseline NMT models on all these three translation tasks. Further analysis also indicates the characteristics of our approaches and details the semantic knowledge that transfered from the discriminator to the NMT model.

关键词： Neural machine translation Sentence alignment Adversarial training

来源：评论

学校读者我要写书评

暂无评论

Efficient Searchable Symmetric Encryption for Storing Multiple Source Data on cloud

Efficient Searchable Symmetric Encryption for Storing Multip...

引用

IEEE International Conference on Trust, Security and Privacy in computing and Communications (TrustCom)

作者： Chang Liu Liehuang Zhu Jinjun Chen Beijing Engineering Research Center of Massive Language Information Processing and Cloud Computing Application School of Computer Science and Technology Beijing Institute of Technology Beijing China Faculty of Engineering and Information Technology University of Technology Sydney NSW Australia

ISBN: (纸本)9781467379533

cloud computing has greatly facilitated large-scale data outsourcing due to its cost efficiency, scalability and many other advantages. Subsequent privacy risks force data owners to encrypt sensitive data, hence making the outsourced data no longer searchable. Searchable Symmetric Encryption (SSE) is an advanced cryptographic primitive addressing the above issue, which maintains efficient keyword search over encrypted data without disclosing much information to the storage provider. Existing SSE schemes implicitly assume that original user data is centralized, so that a searchable index can be built at once. Nevertheless, especially in cloud computing applications, user-side data centralization is not reasonable, e.g. an enterprise distributes its data in several data centers. In this paper, we propose the notion of Multi-Data-Source SSE (MDS-SSE), which allows each data source to build a local index individually and enables the storage provider to merge all local indexes into a global index afterwards. We propose a novel MDS-SSE scheme, in which an adversary only learns the number of data sources, the number of entire data files, the access pattern and the search pattern, but not any other distribution information such as how data files or search results are distributed over data sources. We offer rigorous security proof of our scheme, and report experimental results to demonstrate the efficiency of our scheme.

关键词： Indexes cloud computing Servers Encryption Distributed databases

来源：评论

学校读者我要写书评

暂无评论

Historical information-Based Intent Detection for Multiturn Dialogue 22

Historical Information-Based Intent Detection for Multiturn ...

引用

8th International Conference on computing and Artificial Intelligence, ICCAI 2022

作者： Sun, Xin Zheng, Hongchao Tang, Zheng Beijing Eng. Res. Ctr. of High Vol. Language Information Processing and Cloud Computing Applications School of Computer Science and Technology Beijing Institute of Technology Beijing100081 China School of Computer Science and Technology Beijing Institute of Technology Beijing100081 China

ISBN: (纸本)9781450396110

Intent detection aims to determine the intent of users, an important task in natural language processing and dialogue systems. As one of the key modules of task-based dialogue systems, intent detection directly influences the meaning analysis of spoken language and the performance of dialogue systems. However, existing intent detection algorithms mainly focus on single-turn conversation, ignoring the valuable historical conversation message. To alleviate the problem, we propose a multiturn dialogue intent detection model based on historical information. Specifically, the semantic information of user statements and system statements is extracted by a role-distinguished self-attention network. Then, semantic relevance based on context information adjustment is used to combine the system statement and user statement. Finally, long short-term memory (LSTM) is used to capture the historical message. Experimental results prove that the proposed method improves the effect of intent detection and performs better than seven mainstream baselines. © 2022 ACM.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Design of satellite TV antenna control system for car carrying

引用

International Journal of Wireless and Mobile computing 2013年第4期6卷 412-418页

作者： Yu, Xiao Li, Yuan-Zhang Liang, Qing-Gang Ding, Xiu-Mei Chen, Hong-Liang Liu, Yi-Hao Fan, Kai Tan, Yu-An School of Computer Science and Technology Shandong University of Technology Zibo Shandong China Beijing Eng. Res. Center of Massive Language Information Processing and Cloud Computing Application School of Computer Science Beijing Institute of Technology Beijing China

In this study, we design a satellite TV antenna control system for car carrying with sensor technology, strapdown inertial navigation technology and signal processing technology. The control system uses dsPIC, GPS, 3-axis electronic compass, gyro, tuner and demodulator to work together. The process of system is divided into initial pointing stage and inertial navigation pointing stage. Experimental results show that the system can effectively improve the control accuracy and response speed. Copyright © 2013 Inderscience Enterprises Ltd.

关键词： Global positioning system

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：