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

76 篇 会议
62 篇 期刊文献
1 篇 学位论文

馆藏范围

139 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

135 篇 工学
- 94 篇 计算机科学与技术...
- 51 篇 电气工程
- 22 篇 信息与通信工程
- 18 篇 软件工程
- 14 篇 控制科学与工程
- 9 篇 交通运输工程
- 6 篇 石油与天然气工程
- 5 篇 测绘科学与技术
- 4 篇 动力工程及工程热...
- 4 篇 土木工程
- 2 篇 机械工程
- 2 篇 电子科学与技术（可...
- 2 篇 船舶与海洋工程
- 2 篇 生物医学工程（可授...
- 2 篇 安全科学与工程
- 1 篇 光学工程
28 篇 理学
- 19 篇 物理学
- 3 篇 地球物理学
- 2 篇 数学
- 2 篇 化学
- 1 篇 地理学
- 1 篇 大气科学
- 1 篇 海洋科学
23 篇 医学
- 19 篇 临床医学
- 3 篇 基础医学(可授医学...
9 篇 管理学
- 9 篇 管理科学与工程(可...
- 2 篇 图书情报与档案管...
2 篇 文学
- 2 篇 外国语言文学
1 篇 经济学
- 1 篇 理论经济学
1 篇 教育学
- 1 篇 教育学

主题

139 篇 sequence-to-sequ...
18 篇 deep learning
17 篇 attention mechan...
12 篇 speech synthesis
10 篇 natural language...
8 篇 speech recogniti...
7 篇 transformer
7 篇 attention
6 篇 training
5 篇 transformers
5 篇 decoding
5 篇 feature extracti...
4 篇 semantic segment...
4 篇 transfer learnin...
4 篇 machine learning
4 篇 text-to-speech s...
4 篇 neural machine t...
3 篇 machine translat...
3 篇 automated progra...
3 篇 lstm

机构

3 篇 google mountain ...
3 篇 google llc mount...
2 篇 google res mount...
2 篇 soongsil univ de...
2 篇 nara inst sci & ...
2 篇 soongsil univ sc...
2 篇 nagoya univ info...
2 篇 natl inst inform...
2 篇 univ trento dept...
2 篇 cent china norma...
2 篇 south china univ...
2 篇 fdn bruno kessle...
1 篇 columbia univers...
1 篇 indian inst trop...
1 篇 fdn bruno kessle...
1 篇 city univ hong k...
1 篇 chung ang univ g...
1 篇 jd intelligent c...
1 篇 shandong enginee...
1 篇 ping an technol ...

作者

4 篇 jia ye
4 篇 weiss ron j.
4 篇 bovolo francesca
4 篇 ghosh raktim
4 篇 biadsy fadi
3 篇 moreno pedro j.
3 篇 wu yonghui
2 篇 yamagishi junich...
2 篇 johnson melvin
2 篇 chen youzheng
2 篇 tan xiaoyu
2 篇 ramabhadran bhuv...
2 篇 nakamura satoshi
2 篇 jiang liyang
2 篇 li min
2 篇 lee soowon
2 篇 okamoto takuma
2 篇 kawahara tatsuya
2 篇 wu chung-hsien
2 篇 doshi rohan

语言

138 篇 英文
1 篇 德文
1 篇 法文

检索条件"主题词=sequence-to-sequence Model"

共 139 条记录，以下是121-130 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：

Generating Titles for Web Tables 19

Generating Titles for Web Tables

引用

World Wide Web Conference (WWW)

作者： Hancock, Braden Lee, Hongrae Yu, Cong Stanford Univ Stanford CA 94305 USA Google Mountain View CA USA Google New York NY USA

ISBN: (纸本)9781450366748

Descriptive titles provide crucial context for interpreting tables that are extracted from web pages and are a key component of search features such as tabular featured snippets from Google and Bing. Prior approaches have attempted to produce titles by selecting existing text snippets associated with the table. These approaches, however, are limited by their dependence on suitable titles existing a priori. In our user study, we observe that the relevant information for the title tends to be scattered across the page, and often more than 80% of the time does not appear verbatim anywhere in the page. We propose instead the application of a sequence-to-sequence neural network model as a more generalizable approach for generating high-quality table titles. This is accomplished by extracting many text snippets that have potentially relevant information to the table, encoding them into an input sequence, and using both copy and generation mechanisms in the decoder to balance relevance and readability of the generated title. We validate this approach with human evaluation on sample web tables and report that while sequence models with only a copy mechanism or only a generation mechanism are easily outperformed by simple selection-based baselines, the model with both capabilities performs the best, approaching the quality of crowdsourced titles while training on fewer than ten thousand examples. To the best of our knowledge, the proposed technique is the first to consider text-generation methods for table titles, and establishes a new state of the art.

关键词： title generation web tables table summarization table understanding sequence-to-sequence model text generation pointer-generator network natural language generation

来源：评论

学校读者我要写书评

暂无评论

TACOTRON-BASED ACOUSTIC model USING PHONEME ALIGNMENT FOR PRACTICAL NEURAL TEXT-TO-SPEECH SYSTEMS

TACOTRON-BASED ACOUSTIC MODEL USING PHONEME ALIGNMENT FOR PR...

引用

IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)

作者： Okamoto, Takuma Toda, Tomoki Shiga, Yoshinori Kawai, Hisashi Natl Inst Informat & Commun Technol Tokyo Japan Nagoya Univ Informat Technol Ctr Nagoya Aichi Japan

ISBN: (纸本)9781728103068

Although sequence-to-sequence (seq2seq) models with attention mechanism in neural text-to-speech (TTS) systems, such as Tacotron 2, can jointly optimize duration and acoustic models, and realize high-fidelity synthesis compared with conventional durationacoustic pipeline models, these involve a risk that speech samples cannot be sometimes successfully synthesized due to the attention prediction errors. Therefore, these seq2seq models cannot be directly introduced in practical TTS systems. On the other hand, the conventional pipeline models are broadly used in practical TTS systems since there are few crucial prediction errors in the duration model. For realizing high-quality practical TTS systems without attention prediction errors, this paper investigates Tacotron-based acoustic models with phoneme alignment instead of attention. The phoneme durations are first obtained from HMM-based forced alignment and the duration model is a simple bidirectional LSTM-based network. Then, a seq2seq model with forced alignment instead of attention is investigated and an alternative model with Tacotron decoder and phoneme duration is proposed. The results of experiments with full-context label input using WaveGlow vocoder indicate that the proposed model can realize a high-fidelity TTS system for Japanese with a real-time factor of 0.13 using a GPU without attention prediction errors compared with the seq2seq models.

关键词： Speech synthesis neural text-to-speech duration model forced alignment sequence-to-sequence model

来源：评论

学校读者我要写书评

暂无评论

ENHANCING HYBRID SELF-ATTENTION STRUCTURE WITH RELATIVE-POSITION-AWARE BIAS FOR SPEECH SYNTHESIS 44

ENHANCING HYBRID SELF-ATTENTION STRUCTURE WITH RELATIVE-POSI...

引用

44th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

作者： Yang, Shan Lu, Heng Kang, Shiying Xie, Lei Yu, Dong Northwestern Polytech Univ Sch Comp Sci Xian Shaanxi Peoples R China

ISBN: (纸本)9781479981311

Compared with the conventional "front-end"-"back-end"" vocoder" structure, based on the attention mechanism, end-to-end speech synthesis systems directly train and synthesize from text sequence to the acoustic feature sequence as a whole. Recently, a more calculation efficient end-to-end architecture named transformer, which is solely based on self-attention, was proposed to model global dependencies between the input and output sequences. However, although with many advantages, transformer lacks position information in its structure. Moreover, the weighted sum form in self-attention may disperse the attention to the whole input sequence other than focusing on the more important neighbouring positions. In order to solve the above problems, this paper introduces a hybrid self-attention structure which combines self-attention with the recurrent neural networks (RNNs). We further enhance the proposed structure with relative-position-aware biases. Mean opinion score (MOS) test results indicate that by enhancing hybrid self-attention structure with relative-position-aware biases, the proposed system achieves the best performance with only 0.11 MOS score lower than natural recording.

关键词： text-to-speech synthesis sequence-to-sequence model self-attention relative-position-aware representation

来源：评论

学校读者我要写书评

暂无评论

Personalized Dialogue Response Generation Learned from Monologues 20

Personalized Dialogue Response Generation Learned from Monol...

引用

Interspeech Conference

作者： Su, Feng-Guang Hsu, Aliyah R. Tuan, Yi-Lin Lee, Hung-Yi Natl Taiwan Univ Dept Elect Engn Taipei Taiwan

Personalized responses are essential for having an informative and human-like conversation. Because it is difficult to collect a large amount of dialogues involved with specific speakers, it is desirable that chatbot can learn to generate personalized responses simply from monologues of individuals. In this paper, we propose a novel personalized dialogue generation method which reduces the training data requirement to dialogues without speaker information and monologues of every target speaker. In the proposed approach, a generative adversarial network ensures the responses containing recognizable personal characteristics of the target speaker, and a backward SEQ2SEQ model reconstructs the input message for keeping the coherence of the generated responses. The proposed model demonstrates its flexibility to respond to open-domain conversations, and the experimental results show that the proposed method performs favorably against prior work in coherence, personality classification, and human evaluation.

关键词： personalized dialogue generation generative adversarial network sequence-to-sequence model monologues

来源：评论

学校读者我要写书评

暂无评论

LEVERAGING WEAKLY SUPERVISED DATA TO IMPROVE END-TO-END SPEECH-TO-TEXT TRANSLATION 44

LEVERAGING WEAKLY SUPERVISED DATA TO IMPROVE END-TO-END SPEE...

引用

44th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

作者： Jia, Ye Johnson, Melvin Macherey, Wolfgang Weiss, Ron J. Cao, Yuan Chiu, Chung-Cheng Ari, Naveen Laurenzo, Stella Wu, Yonghui Google Res Mountain View CA 94043 USA

ISBN: (纸本)9781479981311

End-to-end Speech Translation (ST) models have many potential advantages when compared to the cascade of Automatic Speech Recognition (ASR) and text Machine Translation (MT) models, including lowered inference latency and the avoidance of error compounding. However, the quality of end-to-end ST is often limited by a paucity of training data, since it is difficult to collect large parallel corpora of speech and translated transcript pairs. Previous studies have proposed the use of pre-trained components and multi-task learning in order to benefit from weakly supervised training data, such as speech-to-transcript or text-to-foreign-text pairs. In this paper, we demonstrate that using pre-trained MT or text-to-speech (TTS) synthesis models to convert weakly supervised data into speech-to-translation pairs for ST training can be more effective than multi-task learning. Furthermore, we demonstrate that a high quality end-to-end ST model can be trained using only weakly supervised datasets, and that synthetic data sourced from unlabeled monolingual text or speech can be used to improve performance. Finally, we discuss methods for avoiding overfitting to synthetic speech with a quantitative ablation study.

关键词： Speech translation sequence-to-sequence model weakly supervised learning synthetic training data

来源：评论

学校读者我要写书评

暂无评论

Attention model for articulatory features detection 20

Attention model for articulatory features detection

引用

Interspeech Conference

作者： Karaulov, Ievgen Tkanov, Dmytro Sciforce Kharkiv Ukraine

Articulatory distinctive features, as well as phonetic transcription, play important role in speech-related tasks: computer-assisted pronunciation training, text-to-speech conversion (TTS), studying speech production mechanisms, speech recognition for low-resourced languages. End-to-end approaches to speech-related tasks got a lot of traction in recent years. We apply Listen, Attend and Spell (LAS) [1] architecture to phones recognition on a small small training set, like TIMIT [2]. Also, we introduce a novel decoding technique that allows to train manners and places of articulation detectors end-to-end using attention models. We also explore joint phones recognition and articulatory features detection in multitask learning setting.

关键词： manners of articulation places of articulation sequence-to-sequence model multitask learning low-resource speech recognition phones recognition

来源：评论

学校读者我要写书评

暂无评论

Routine modeling with Time Series Metric Learning 28th

Routine Modeling with Time Series Metric Learning

引用

28th International Conference on Artificial Neural Networks (ICANN)

作者： Compagnon, Paul Lefebvre, Gregoire Duffner, Stefan Garcia, Christophe Orange Labs Grenoble France CNRS LIRIS INSA Lyon UMR 5205 Lyon France

ISBN: (纸本)9783030304843;9783030304836

Traditionally, the automatic recognition of human activities is performed with supervised learning algorithms on limited sets of specific activities. This work proposes to recognize recurrent activity patterns, called routines, instead of precisely defined activities. The modeling of routines is defined as a metric learning problem, and an architecture, called SS2S, based on sequence-to-sequence models is proposed to learn a distance between time series. This approach only relies on inertial data and is thus non intrusive and preserves privacy. Experimental results show that a clustering algorithm provided with the learned distance is able to recover daily routines.

关键词： Metric learning sequence-to-sequence model Activity recognition Time series Inertial data

来源：评论

学校读者我要写书评

暂无评论

A Context based Coverage model for Abstractive Document Summarization 10

A Context based Coverage Model for Abstractive Document Summ...

引用

10th International Conference on Information and Communication Technology Convergence (ICTC) - ICT Convergence Leading the Autonomous Future

作者： Kim, Heechan Lee, Soowon Soongsil Univ Dept Software Convergence Seoul South Korea Soongsil Univ Sch Software Seoul South Korea

ISBN: (纸本)9781728108933

Automatic abstractive summarization is one of natural language processing fields that generates a sequence of words representing important information of the input document. The sequence-to-sequence model, which is widely used in abstractive summarization, has a repetition problem in which the same sub-pattern is repeatedly generated in decode phases. To solve this problem, various coverage models have been proposed in machine translation. In automatic summarization, unlike machine translation, the lengths of input and summary documents are very different. Because the summary document is a compressed form of important meaning of the input document. Due to the nature of automatic summarization, it is difficult to apply a word position-based coverage model in machine translation directly. For automatic summarization, we propose a context based coverage model to consider the coverage based on the compressed meaning of the input document. The context based coverage is defined as the accumulated weighted average of the encoded word meaning by the attention scores. This considers the meaning of words rather than the position of words in the input document. In the experiment with CNN/DailyMail dataset, the proposed model shows better performance than the previous researches.

关键词： Context Coverage sequence-to-sequence model Abstractive Document Summarization Natural Language Processing

来源：评论

学校读者我要写书评

暂无评论

Improving Neural Response Diversity with Frequency-Aware Cross-Entropy Loss 19

Improving Neural Response Diversity with Frequency-Aware Cro...

引用

World Wide Web Conference (WWW)

作者： Jiang, Shaojie Ren, Pengjie Monz, Christof de Rijke, Maarten Univ Amsterdam Amsterdam Netherlands

ISBN: (纸本)9781450366748

sequence-to-sequence (Seq2Seq) models have achieved encouraging performance on the dialogue response generation task. However, existing Seq2Seq-based response generation methods suffer from a low-diversity problem: they frequently generate generic responses, which make the conversation less interesting. In this paper, we address the low-diversity problem by investigating its connection with model over-confidence reflected in predicted distributions. Specifically, we first analyze the influence of the commonly used Cross-Entropy (CE) loss function, and find that the CE loss function prefers high-frequency tokens, which results in low-diversity responses. We then propose a Frequency-Aware CrossEntropy (FACE) loss function that improves over the CE loss function by incorporating a weighting mechanism conditioned on token frequency. Extensive experiments on benchmark datasets show that the FACE loss function is able to substantially improve the diversity of existing state-of-the-art Seq2Seq response generation methods, in terms of both automatic and human evaluations.

关键词： Chatbot Dialogue system sequence-to-sequence model

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Based LSTM and SeqToSeq models to Detect Monsoon Spells of India 19th

Deep Learning Based LSTM and SeqToSeq Models to Detect Monso...

引用

19th Annual International Conference on Computational Science (ICCS)

作者： Viswanath, Saicharan Saha, Moumita Mitra, Pabitra Nanjundiah, Ravi S. Natl Inst Technol Karnataka Surathkal India Indian Inst Sci Ctr Atmospher & Ocean Sci Bangalore Karnataka India Indian Inst Technol Kharagpur Kharagpur W Bengal India Indian Inst Sci Divecha Ctr Climate Change Bangalore Karnataka India Indian Inst Trop Meteorol Pune Maharashtra India

ISBN: (纸本)9783030227418;9783030227401

Monsoon spells are important climatic phenomenon modulating the quality and quantity of monsoon over a year. India being an agricultural country, identification of monsoon spells is extremely important to plan agricultural policies following the phases of monsoon to attain maximum productivity. Monsoon spells' detection involve analyzing and predicting monsoon at daily levels which make it more challenging as daily-variability is higher as compared to monsoon over a month or an year. In this article, deep-learning based long short-term memory and sequence-to-sequence models are utilized to classify monsoon days, which are finally assembled to detect the spells. Dry and wet days are classified with precision of 0.95 and 0.87, respectively. Break spells are observed to be forecast with higher accuracy than the active spells. Additionally, sequence-to-sequence model is noted to perform superior to that of long-short term memory model. The proposed models also outperform traditional classification models for monsoon spell detection.

关键词： Active spell Break spell Long short term memory sequence-to-sequence model Attention mechanism Classification Spells' detection

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14页 << < 5 6 7 8 9 10 11 12 13 14 > >>

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：