检索结果-内蒙古大学图书馆

您好，读者！请登录

内蒙古大学图书馆

首页
概况
党建
资源
服务
科研支持
- 论文收录引用证明
- 科技查新
知识产权
档案馆
帮助

咨询与建议

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

您的常用邮箱：*

您的手机号码：*

问题描述：

当前已输入0个字，您还可以输入200个字

全部搜索
期刊论文
图书
学位论文
标准
纸本馆藏
外文资源发现
数据库导航
超星发现

高级检索

时间限定

出版年份：

文献类型

图书期刊文献学位论文多媒体

馆藏选择

电子馆藏纸本馆藏

核心期刊

全部期刊 SCI 收录期刊 SSCI 收录期刊 EI 收录期刊 CSCD 收录期刊 CSSCI 收录期刊

语言

中文英文

文献类型

期刊文献图书学位论文标准纸本馆藏

帮助

文字说明：

T=题名（书名、题名），A=作者（责任者），K=主题词，P=出版物名称，PU=出版社名称，O=机构（作者单位、学位授予单位、专利申请人），L=中图分类号，C=学科分类号，U=全部字段，Y=年（出版发行年、学位年度、标准发布年）

检索规则说明：

AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：

范例一：(K=图书馆学 OR K=情报学) AND A=范并思 AND Y=1982-2016
范例二：P=计算机应用与软件 AND (U=C++ OR U=Basic) NOT K=Visual AND Y=2011-2016

分类表

所选分类

>> <<

限定检索结果

文献类型

75 篇 会议
29 篇 期刊文献

馆藏范围

104 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

83 篇 工学
- 50 篇 计算机科学与技术...
- 32 篇 软件工程
- 20 篇 信息与通信工程
- 15 篇 电气工程
- 9 篇 控制科学与工程
- 3 篇 机械工程
- 2 篇 电子科学与技术（可...
- 2 篇 土木工程
- 2 篇 交通运输工程
- 2 篇 生物医学工程（可授...
- 1 篇 力学（可授工学、理...
- 1 篇 建筑学
- 1 篇 城乡规划学
- 1 篇 生物工程
- 1 篇 网络空间安全
13 篇 管理学
- 13 篇 管理科学与工程(可...
8 篇 理学
- 6 篇 数学
- 3 篇 系统科学
4 篇 教育学
- 4 篇 心理学(可授教育学...
4 篇 医学
- 4 篇 基础医学(可授医学...
- 2 篇 临床医学
3 篇 文学
- 3 篇 外国语言文学
1 篇 农学
- 1 篇 作物学

主题

104 篇 object oriented ...
35 篇 language
13 篇 machine translat...
11 篇 original languag...
10 篇 semantics
8 篇 speech recogniti...
7 篇 modelling langua...
6 篇 translation proc...
6 篇 object-oriented ...
6 篇 english
6 篇 translations
6 篇 neural network
6 篇 translation
6 篇 english language
5 篇 object orientati...
5 篇 speech
5 篇 java
5 篇 dictionaries as ...
5 篇 belgo-luxembourg...
5 篇 word

机构

2 篇 ku leuven - esat...
1 篇 key laboratory o...
1 篇 department of co...
1 篇 usn res lab char...
1 篇 purdue univ dept...
1 篇 china ship res &...
1 篇 sintef digital o...
1 篇 dmi university o...
1 篇 univ informat te...
1 篇 german research ...
1 篇 3lt/supgt lab de...
1 篇 osaka univ grad ...
1 篇 dublin city univ...
1 篇 school of comput...
1 篇 national laborat...
1 篇 department of co...
1 篇 univ verona dipa...
1 篇 limsi-cnrs
1 篇 university of te...
1 篇 rutgers state un...

作者

2 篇 dirk van compern...
2 篇 reza sahraeian
2 篇 zoltan tuske
2 篇 christof monz
2 篇 ralf schluter
2 篇 marcello federic...
1 篇 hung-yi lee
1 篇 oliveira bruno c...
1 篇 amparo varona
1 篇 conghui zhu
1 篇 lei wang
1 篇 patrick th. eugs...
1 篇 rachid guerraoui
1 篇 arianna bisazza
1 篇 matejak marek
1 篇 alastair wilcox
1 篇 philippe balbian...
1 篇 a. mohan
1 篇 nestmann u
1 篇 spyros martzouko...

语言

98 篇 英文
4 篇 其他
2 篇 中文

检索条件"主题词=Object Oriented Programming Languages"

共 104 条记录，以下是11-20 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

Efficient methods to train multilingual bottleneck feature extractors for low resource keyword search

Efficient methods to train multilingual bottleneck feature e...

引用

IEEE International Conference on Acoustics, Speech and Signal Processing

作者： Chongjia Ni Cheung-Chi Leung Lei Wang Nancy F. Chen Bin Ma Institute for Infocomm Research (I2R) A*STAR Singapore

ISBN: (纸本)9781509041183

Training a bottleneck feature (BNF) extractor with multilingual data has been common in low resource keyword search. In a low resource application, the amount of transcribed target language data is limited while there are usually plenty of multilingual data. In this paper, we investigated two methods to train efficient multilingual BNF extractors for low resource keyword search. One method is to use the target language data to update an existing BNF extractor, and another method is to combine the target language data to train a new multilingual BNF extractor from the start. In these two methods, we proposed to use long short-term memory recurrent neural network based language identification to select utterances in the multilingual training data that are acoustically close to the target language. Experiments on Swahili in the OpenKWS15 data demonstrated the efficiency of our proposed methods. The first method facilitates rapid system development, while both methods outperform using baseline BNF extractors in terms of accuracy.

关键词： Keyword spotting multilingual data selection recurrent neural network language identification recurrent neural nets language recognition extraction device object oriented programming languages BACKUS-NAUR FORM biological nitrogen fixation Key Search Systems development Swahili TRAIN

来源：评论

学校读者我要写书评

暂无评论

A Character-based Convolutional Neural Network for Language-Agnostic Twitter Sentiment Analysis

A Character-based Convolutional Neural Network for Language-...

引用

International Joint Conference on Neural Networks

作者： Jonatas Wehrmann Willian Becker Henry E. L. Cagnini Rodrigo C. Barros Faculdade de Informática Pontifícia Universidade Católica do Rio Grande do Sul Av. Ipiranga 6681 90619-900 Porto Alegre RS Brazil

ISBN: (纸本)9781509061839

Most work on tweet sentiment analysis is monolingual and the models that are generated by machine learning strategies do not generalize across multiple languages. Cross-language sentiment analysis is usually performed through machine translation approaches that translate a given source language into the target language of choice. Machine translation is expensive and the results that are provided by theses strategies are limited by the quality of the translation that is performed. In this paper, we propose a language-agnostic translation-free method for Twitter sentiment analysis, which makes use of deep convolutional neural networks with character-level embeddings for pointing to the proper polarity of tweets that may be written in distinct (or multiple) languages. The proposed method is more accurate than several other deep neural architectures while requiring substantially less learnable parameters. The resulting model is capable of learning latent features from all languages that are employed during the training process in a straightforward fashion and it does not require any translation process to be performed whatsoever. We empirically evaluate the efficiency and effectiveness of the proposed approach in tweet corpora based on tweets from four different languages, showing that our approach comfortably outperforms the baselines. Moreover, we visualize the knowledge that is learned by our method to qualitatively validate its effectiveness for tweet sentiment classification.

关键词： Sentiment analysis Twitter Neural networks Context Analytical models Training Vocabulary TWITTER Neural network Social Media Sentiment analysis ANALYSIS MODELS Vocabulary Functional training Language original language object oriented programming languages machine translation Translation Process Training

来源：评论

学校读者我要写书评

暂无评论

Exploiting sequential Low-Rank Factorization for multilingual DNNS

Exploiting sequential Low-Rank Factorization for multilingua...

引用

IEEE International Conference on Acoustics, Speech and Signal Processing

作者： Reza Sahraeian Dirk Van Compernolle KU Leuven - ESAT Kasteelpark Arenberg 10 3001 Heverlee Belgium

ISBN: (纸本)9781509041183

DNNs have shown remarkable performance in multilingual scenarios;however, these models are often too large in size that adaptation to a target language with relatively small amount of data cannot be well accomplished. In our previous work, we utilized Low-Rank Factorization (LRF) using singular value decomposition for multilingual DNNs to learn compact models which can be adapted more successfully. In this paper, we address two problems associated with that LRF scheme and we propose a compellingly simple methodology to overcome them. First, factorizing all layers results in a huge drop in performance and consequently a long recovery process is required which is not practically efficient. Secondly, LRF can be viewed as a regularization by which some noise is added to weight layers;however, factorizing all layers together equates to adding too much noise which results in bad performance. To mitigate these problems, we propose to apply LRF sequentially. We demonstrate that the lost information after factorizing one layer is small and can be rapidly retrieved;hence, sequential factorization is more efficient. Moreover, the sequential LRF adds only a small amount of noise sequentially which is a better regularization. Our experiments are conducted on five languages from the GlobalPhone dataset.

关键词： Multilingual DNNs low-rank factorization factorization object oriented programming languages Noise Sequential one layer Singular value decomposition Low-rank coal

来源：评论

学校读者我要写书评

暂无评论

Effective articulatory modeling for pronunciation error detection of L2 learner without non-native training data

Effective articulatory modeling for pronunciation error dete...

引用

IEEE International Conference on Acoustics, Speech and Signal Processing

作者： Richeng Duan Tatsuya Kawahara Masatake Dantsuji Jinsong Zhang School of Informatics Kyoto University Sakyo-ku 606-8501 Japan Academic Center for Computing and Media Studies Kyoto University Japan School of Information Science Beijing Language and Culture University China

ISBN: (纸本)9781509041183

For effective articulatory feedback in computer-assisted pronunciation training (CAPT) systems, we address effective articulatory models of second language (L2) learners' speech without using such data, which is difficult to collect and annotate in a large scale. Context-dependent articulatory attributes (placement and manner of articulation) are modeled based on deep neural network (DNN). In order to efficiently train the non-native articulatory models, we exploit large speech corpora of native and target language to model inter-language phenomena. This multi-lingual learning is then combined with multi-task learning, which uses phone-classification as a sub-task. These methods are applied to Mandarin Chinese pronunciation learning by Japanese native speakers. Effects are confirmed in the native attribute classification and pronunciation error detection of non-native speech.

关键词： Computer-assisted pronunciation training (CAPT) pronunciation error detection articulation modeling DNN multi-lingual learning Pronunciation Error detection object oriented programming languages Introduced species Speech Joints Training data

来源：评论

学校读者我要写书评

暂无评论

PREDICTION-ADAPTATION-CORRECTION RECURRENT NEURAL NETWORKS FOR LOW-RESOURCE LANGUAGE SPEECH RECOGNITION

PREDICTION-ADAPTATION-CORRECTION RECURRENT NEURAL NETWORKS F...

引用

IEEE International Conference on Acoustics, Speech and Signal Processing

作者： Yu Zhang Ekapol Chuangsuwanich James Glass Dong Yu MIT Computer Science and Artificial Intelligence Laboratory Microsoft Research

ISBN: (纸本)9781479999897

In this paper, we investigate the use of prediction-adaptation-correction recurrent neural networks (PAC-RNNs) for lowresource speech recognition. A PAC-RNN is comprised of a pair of neural networks in which a correction network uses auxiliary information given by a prediction network to help estimate the state probability. The information from the correction network is also used by the prediction network in a recurrent loop. Our model outperforms other state-of-the-art neural networks (DNNs, LSTMs) on IARPA-Babel tasks. Moreover, transfer learning from a language that is similar to the target language can help improve performance further.

关键词： DNN LSTM PAC-RNN Multilingual Neural network Speech recognition object oriented programming languages Multilingualism Transfer (Psychology) Language WWOX gene Network

来源：评论

学校读者我要写书评

暂无评论

MACHINE TRANSLATION BASED DATA AUGMENTATION FOR CANTONESE KEYWORD SPOTTING

MACHINE TRANSLATION BASED DATA AUGMENTATION FOR CANTONESE KE...

引用

IEEE International Conference on Acoustics, Speech and Signal Processing

作者： Guangpu Huang Arseniy Gorin Jean-Luc Gauvain Lori Lamel LIMSI CNRS Spoken Language Processing Group 91405 Orsay Cedex France

ISBN: (纸本)9781479999897

This paper presents a method to improve a language model for a limited-resourced language using statistical machine translation from a related language to generate data for the target language. In this work, the machine translation model is trained on a corpus of parallel Mandarin-Cantonese subtitles and used to translate a large set of Mandarin conversational telephone transcripts to Cantonese, which has limited resources. The translated transcripts are used to train a more robust language model for speech recognition and for keyword search in Cantonese conversational telephone speech. This method enables the keyword search system to detect 1.5 times more out-of-vocabulary words, and achieve 1.7% absolute improvement on actual term-weighted value.

关键词： keyword spotting data augmentation language modelling neural networks low-resourced languages modelling languages machine translation Neural network object oriented programming languages Key Search Cantonese KEYWORD

来源：评论

学校读者我要写书评

暂无评论

Analyzing Chinese English by the functional equivalence theory

Analyzing Chinese English by the functional equivalence theo...

引用

2016 4th International Conference on Management Science,Education Technology,Arts,Social Science and Economics(MSETASSE 2016)

作者： Zhao Hui Min Bohai university

ISBN: (纸本)9781510834071

Over the past few years, with China's rising international status, the international arena has a more right to speak. The emergence of a large number of words with Chinese characteristics has played an important role in China's propaganda. When the eastern and Western cultures are blended, it is the most important task for the translators to spread the Chinese and Western culture to the western countries. The essence of translation is to translate one language into another, which is communicated to the audience. Translation theory is often divided into translation and interpretation, translation and translation skills such as transliteration, literal translation and free translation techniques, analysis of the basic skills of interpreting translation skills for the purpose of this paper is to reference the translation. The famous American translation theorist Nida "s Functional Equivalence Based on the theory, he believes that between the source language and the target language can be achieved at four levels of equivalence: vocabulary equivalence, syntactic equivalence, stylistic equivalence and textual equivalence. This paper analyzes the application of translation methods such as transliteration, literal translation and free translation from four levels of equivalence, and explores the translation of Chinese characteristics into English This paper discusses the English translation of Chinese tourism texts from the perspective of functional equivalence.

关键词： Functional equivalence theory Chinese English Chinese characteristics English translation skills Translation strategies Translations Translation functionally equivalent Translation Process equivalence original language European cultures object oriented programming languages Chinese Chinese philosophy Chinese art English English language translator basic skill

来源：评论

学校读者我要写书评

暂无评论

LEARNING CROSS-LINGUAL INFORMATION WITH MULTILINGUAL BLSTM FOR SPEECH SYNTHESIS OF LOW-RESOURCE languages

LEARNING CROSS-LINGUAL INFORMATION WITH MULTILINGUAL BLSTM F...

引用

IEEE International Conference on Acoustics, Speech and Signal Processing

作者： Quanjie Yu Peng Liu Zhiyong Wu Shiyin Kang Helen Meng Lianhong Cai Tsinghua-CUHK Joint Research Center for Media Sciences Technologies and Systems Graduate School at Shenzhen Tsinghua University Shenzhen 518055 China Department of Systems Engineering and Engineering Management The Chinese University of Hong Kong Shatin N.T. Hong Kong SAR China

ISBN: (纸本)9781479999897

Bidirectional long short-term memory (BLSTM) based speech synthesis has shown great potential in improving the quality of the synthetic speech. However, for low-resource languages, it is difficult to obtain a high quality BLSTM model. BLSTM based speech synthesis can be viewed as a transformation between the input features and the output features. We assume that the input and output layers of BLSTM are language-dependent while the hidden layers can be language-independent if trained properly. We investigate whether sufficient training data of another language (auxiliary) can benefit the BLSTM training of a new language (target) that has only limited training data. In this paper, we propose 1) a multilingual BLSTM that shares hidden layers across different languages and 2) a specific training approach that can best utilize the training data from both the auxiliary and target languages. Experimental results demonstrate the effectiveness of the proposed approach. The multilingual BLSTM can learn the cross-lingual information, and can predict more accurate acoustic features for speech synthesis of the target language than the monolingual BLSTM that is trained with only the data from the target language. Subjective test also indicates that multilingual BLSTM outperforms the monolingual BLSTM in generating higher quality synthetic speech.

关键词： Speech synthesis bidirectional long shortterm memory (BLSTM) low-resource multilingual cross-lingual Speech synthesis object oriented programming languages Language Multilingualism Training data language-independent biological control

来源：评论

学校读者我要写书评

暂无评论

A Logical Theory of Belief Dynamics for Resource-Bounded Agents 16

A Logical Theory of Belief Dynamics for Resource-Bounded Age...

引用

International Conference on Autonomous Agents and Multiagent Systems

作者： Philippe Balbiani David Fernandez-Duque Emiliano Lorini IRIT-CNRS Toulouse University IRIT Toulouse University

ISBN: (纸本)9781510855083

The paper presents a new logic for reasoning about the formation of beliefs through perception or through inference in non-omniscient resource-bounded agents. The logic distinguishes the concept of explicit belief from the concept of background knowledge. This distinction is reflected in its formal semantics and axiornatics: (i) we use a non-standard semantics putting together a neighbourhood semantics for explicit beliefs and relational semantics for background knowledge, and (ii) we have specific axioms in the logic high-lighting the relationship between the two concepts Mental operations of perceptive type and inferential type, having effects on epistemic states of agents, are primitives in the object language of the logic. At the semantic level, they are modelled as special kinds of model-update operations, in the style of dynamic epistemic logic (DEL). Results about axiomatization, decidability and complexity for the logic are given in the paper.

关键词： Theory Epistemic logic Cognitive agents Resource-bounded reasoning Formal logic Beliefs Semantics object oriented programming languages semiotics Agents theories non-standard

来源：评论

学校读者我要写书评

暂无评论

A STUDY OF RANK-CONSTRAINED MULTILINGUAL DNNS FOR LOW-RESOURCE ASR

A STUDY OF RANK-CONSTRAINED MULTILINGUAL DNNS FOR LOW-RESOUR...

引用

IEEE International Conference on Acoustics, Speech and Signal Processing

作者： Reza Sahraeian Dirk Van Compernolle KU Leuven - ESAT Kasteelpark Arenberg 10 3001 Heverlee Belgium

ISBN: (纸本)9781479999897

Multilingual Deep Neural Networks (DNNs) have been successfully used to exploit out-of-language data to improve under-resourced ASR. In this paper, we improve on a multilingual DNN by utilizing low-rank factorization (LRF) of weight matrices via Singular Value Decomposition (SVD) to sparsify a multilingual DNN. LRF was previously used for monolingual DNNs, yielding large computational savings without a significant loss in recognition accuracy. In this work, we show that properly applying LRF on a multilingual DNN can improve recognition accuracy for multiple low-resource ASR configurations. First, only the final weight layer is factorized. Since the output weight layer needs to be trained with language specific data, reducing the number of parameters is beneficial for under-resourced languages. It is common in multilingual DNN speech recognition, to further adapt the full neural network through retraining of the multilingual DNN on target language data. Again we observe that in low-resource situations, this adaptation can bring significant improvement if LRF is applied to all hidden layers. We demonstrate the positive effect of LRF in two very different scenarios: one is a phone recognition task for two related languages and the other is a word recognition task using five different languages from the GlobalPhone dataset.

关键词： Multilingual deep neural network low-rank factorization low-resource ASR Speech recognition aquifer storage and recovery CREBRF gene Language word recognition Vocational Rehabilitation Singular value decomposition Low-rank coal Recognition (Psychology) Neural network language data object oriented programming languages

来源：评论

学校读者我要写书评

暂无评论

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共11页 << < 1 2 3 4 5 6 7 8 9 10 > >>

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

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：