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101-110 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：

Category Recognition in E-Commerce using sequence-to-sequence Hierarchical Classification 21

Category Recognition in E-Commerce using Sequence-to-Sequenc...

引用

14th ACM International Conference on Web Search and Data Mining (WSDM)

作者： Hasson, Idan Novgorodov, Slava Fuchs, Gilad Acriche, Yoni eBay Res San Jose CA 95125 USA

ISBN: (纸本)9781450382977

E-commerce platforms often use a predefined structured hierarchy of product categories. Apart from helping buyers sort between different product types, listing categorization is also critical for multiple downstream tasks, including the platform's main listing search. Traditionally, when creating a new listing, sellers need to assign the product they sell to a single category. However, the high diversity of product types in the platform, along with the hierarchy's low level of granularity result in tens of thousands of different possible categories that sellers need to pick from. This, in turn, creates a unique classification challenge, especially for sellers with a large number of listings. Moreover, the expected cost of making a category classification error is high, as it can impact the likelihood that their listing will get discovered by relevant buyers, and eventually sold. To help with the challenge of category recognition we present CATRECOMM - an interactive real-time system that is generalized to provide category recommendations in different e-commerce scenarios. We present results from using the system for two main sub-tasks - listing and search-query category recognition, and demonstrate an end-to-end scenario of the former one. The system uses a convolutional sequence-to-sequence approach, and to the best of our knowledge, is the first to use this approach for category recognition. We define a new metric for evaluating this model which captures the hierarchical characteristics of the data and supports displaying multiple classification results. Finally, our experimental results show the effectiveness and efficiency on real-world data.

关键词： sequence-to-sequence model hierarchical classification e-commerce machine learning

来源：评论

学校读者我要写书评

暂无评论

Conformer Parrotron: a Faster and Stronger End-to-end Speech Conversion and Recognition model for Atypical Speech 22

Conformer Parrotron: a Faster and Stronger End-to-end Speech...

引用

Interspeech Conference

作者： Chen, Zhehuai Ramabhadran, Bhuvana Biadsy, Fadi Zhang, Xia Chen, Youzheng Jiang, Liyang Chu, Fang Doshi, Rohan Moreno, Pedro J. Google LLC Mountain View CA 94043 USA

ISBN: (纸本)9781713836902

Parrotron is an end-to-end personalizable model that enables many-to-one voice conversion (VC) and automated speech recognition (ASR) simultaneously for atypical speech. In this work, we present the next-generation Parrotron model with improvements in overall accuracy, training and inference speeds. The proposed architecture builds on the recent Conformer encoder comprising of convolution and attention layer based blocks used in ASR. We introduce architectural modifications that subsamples encoder activations to achieve speed-ups in training and inference. In order to jointly improve ASR and voice conversion quality, we show that this requires a corresponding upsampling after the Conformer encoder blocks. We provide an in-depth analysis on how the proposed approach can maximize the efficiency of a speech-to-speech conversion model in the context of atypical speech. Experiments on both many-to-one and one-to-one dysarthric speech conversion tasks show that we can achieve up to 7X speedup and 35% relative reduction in WER over the previous best Transformer Parrotron.

关键词： voice conversion speech impairments sequence-to-sequence model speech recognition

来源：评论

学校读者我要写书评

暂无评论

END-TO-END MULTIMODAL SPEECH RECOGNITION

END-TO-END MULTIMODAL SPEECH RECOGNITION

引用

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

作者： Palaskar, Shruti Sanabria, Ramon Metze, Florian Carnegie Mellon Univ Pittsburgh PA 15213 USA

ISBN: (纸本)9781538646588

Transcription or sub-titling of open-domain videos is still a challenging domain for Automatic Speech Recognition (ASR) due to the data's challenging acoustics, variable signal processing and the essentially unrestricted domain of the data. In previous work, we have shown that the visual channel - specifically object and scene features - can help to adapt the acoustic model (AM) and language model (LM) of a recognizer, and we are now expanding this work to end-to-end approaches. In the case of a Connectionist Temporal Classification (CTC)-based approach, we retain the separation of AM and LM, while for a sequence-to-sequence (S2S) approach, both information sources are adapted together, in a single model. This paper also analyzes the behavior of CTC and S2S models on noisy video data (How-To corpus), and compares it to results on the clean Wall Street Journal (WSJ) corpus, providing insight into the robustness of both approaches.

关键词： Audiovisual Speech Recognition Connectionist Temporal Classification sequence-to-sequence model Adaptation

来源：评论

学校读者我要写书评

暂无评论

Text-to-SQL Generation for Question Answering on Electronic Medical Records 20

Text-to-SQL Generation for Question Answering on Electronic ...

引用

29th World Wide Web Conference (WWW)

作者： Wang, Ping Shi, Tian Reddy, Chandan K. Virginia Tech Dept Comp Sci Arlington VA 22203 USA

ISBN: (纸本)9781450370233

Electronic medical records (EMR) contain comprehensive patient information and are typically stored in a relational database with multiple tables. Effective and efficient patient information retrieval from EMR data is a challenging task for medical experts. Question-to-SQL generation methods tackle this problem by first predicting the SQL query for a given question about a database, and then, executing the query on the database. However, most of the existing approaches have not been adapted to the healthcare domain due to a lack of healthcare Question-to-SQL dataset for learning models specific to this domain. In addition, wide use of the abbreviation of terminologies and possible typos in questions introduce additional challenges for accurately generating the corresponding SQL queries. In this paper, we tackle these challenges by developing a deep learning based TRanslate-Edit model for Question-to-SQL (TREQS) generation, which adapts the widely used sequence-to-sequence model to directly generate the SQL query for a given question, and further performs the required edits using an attentive-copying mechanism and task-specific look-up tables. Based on the widely used publicly available electronic medical database, we create a new large-scale Question-SQL pair dataset, named MIMICSQL, in order to perform the Question-to-SQL generation task in healthcare domain. An extensive set of experiments are conducted to evaluate the performance of our proposed model on MIMICSQL. Both quantitative and qualitative experimental results indicate the flexibility and efficiency of our proposed method in predicting condition values and its robustness to random questions with abbreviations and typos.

关键词： sequence-to-sequence model attention mechanism pointer-generator network electronic medical records SQL query

来源：评论

学校读者我要写书评

暂无评论

A Hybrid CNN-Transformer Architecture for Semantic Segmentation of Radar Sounder data

A Hybrid CNN-Transformer Architecture for Semantic Segmentat...

引用

IEEE International Geoscience and Remote Sensing Symposium (IGARSS)

作者： Ghosh, Raktim Bovolo, Francesca Univ Trento FBK Trento Italy FBK Trento Italy

ISBN: (数字)9781665427920

ISBN: (纸本)9781665427920

Radar Sounders (RSs) are space-borne and airborne sensors operating on the nadir-looking geometry to collect subsurface information by transmitting linearly modulated electromagnetic (EM) pulses and receiving backscattered (reflected from different subsurface targets) echoes. The echoes are coherently represented to generate radargrams. A radargram is used to characterize subsurface target structures. Interestingly, radargram signals depict sequential structures due to linearly homogeneous subsurface target features such as ice layers. Several automatic techniques are proposed to characterize the subsurface targets in the radargrams mostly associated with the probabilistic models or CNN-based deep learning models. The CNN-based architectures explicitly model the local spatial high dimensional contexts which are often infeasible for establishing the long-range sequential contextual relationship between local spatial features. Motivated by the aforementioned fact, we propose a hybrid CNN-Transformer-based encoder-decoder architectural framework for addressing the long-range sequential contextual dependencies within the sequential structures of RS signals. We tested the architecture on Multi-channel Coherent Radar Depth Sounder (MCoRDS) dataset. Experimental results confirm the capability of Transformers to characterize the subsurface targets.

关键词： Semantic Segmentation Transformers sequence-to-sequence model Radar Sounder

来源：评论

学校读者我要写书评

暂无评论

EFFECT OF CHOICE OF PROBABILITY DISTRIBUTION, RANDOMNESS, AND SEARCH METHODS FOR ALIGNMENT modelING IN sequence-TO-sequence TEXT-TO-SPEECH SYNTHESIS USING HARD ALIGNMENT

EFFECT OF CHOICE OF PROBABILITY DISTRIBUTION, RANDOMNESS, AN...

引用

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

作者： Yasuda, Yusuke Wang, Xin Yamagishi, Junichi Natl Inst Informat Chiyoda City Tokyo Japan SOKENDAI Miura Dist Kanagawa Japan

ISBN: (纸本)9781509066315

sequence-to-sequence text-to-speech (TTS) is dominated by soft-attention-based methods. Recently, hard-attention-based methods have been proposed to prevent fatal alignment errors, but their sampling method of discrete alignment is poorly investigated. This research investigates various combinations of sampling methods and probability distributions for alignment transition modeling in a hard-alignment-based sequence-to-sequence TTS method called SSNT-TTS. We clarify the common sampling methods of discrete variables including greedy search, beam search, and random sampling from a Bernoulli distribution in a more general way. Furthermore, we introduce the binary Concrete distribution to model discrete variables more properly. The results of a listening test shows that deterministic search is more preferable than stochastic search, and the binary Concrete distribution is robust with stochastic search for natural alignment transition.

关键词： speech synthesis deep learning sequence-to-sequence model

来源：评论

学校读者我要写书评

暂无评论

TBCUP: A Transformer-based Code Comments Updating Approach 47

TBCUP: A Transformer-based Code Comments Updating Approach

引用

47th IEEE-Computer-Society Annual International Conference on Computers, Software, and Applications (COMPSAC)

作者： Liu, Shifan Cui, Zhanqi Chen, Xiang Yang, Jun Li, Li Zheng, Liwei Beijing Informat Sci & Technol Univ Sch Comp Sci Beijing Peoples R China Nantong Univ Sch Informat Sci & Technol Nantong Peoples R China

ISBN: (纸本)9798350326970

Good code comments are of great value for program maintenance. However, during the development process, developers often neglect to update the corresponding comments when changing the code, which results in inconsistent comments and affects the maintainability of software. Studies have shown that even in widely used programs, there is a large number of outdated comments. Existing code comment update approaches use long short-term memory (LSTM) model based on encoder-decoder to capture the relationship between code changes and comment updates, to automatically update code comments. However, due to the complexity of code changes, the corresponding comments update results do not perform well. Thus, a Transformer-based automatic update approach for code comments called TBCUP is proposed in this paper. TBCUP uses the multi-head attention mechanism to learn the relationship between code change sequences and comment updates to update comments more accurately. In addition, TBCUP uses the Byte Pair Encoding (BPE) algorithm to build a unified vocabulary for code and corresponding comments to alleviate the problem of out-of-vocabulary (OOV) words while updating comments. With BPE, TBCUP can split or combine words to handle OOV words. The experimental results on the dataset containing 108k sets of code-comment co-evolution samples show that the accuracy of TBCUP is improved by 3.2% in comparison with CUP.

关键词： program comprehension comment updating deep learning sequence-to-sequence model code changes

来源：评论

学校读者我要写书评

暂无评论

UCSC-CGEC: A Unified Approach For Chinese Spelling Check And Grammatical Error Correction

UCSC-CGEC: A Unified Approach For Chinese Spelling Check And...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Su, Jindian Xie, Yunhao Mou, Yueqi South China Univ Technol Sch Comp Sci & Engn Guangzhou Peoples R China South China Univ Technol Sch Software Engn Guangzhou Peoples R China

ISBN: (纸本)9798350359329;9798350359312

Chinese Spelling Check (CSC) and Chinese Grammatical Error Correction (CGEC) are two important and challenging tasks in the Natural Language Processing (NLP) field. The former aims to detect and correct Chinese misspellings while the latter focuses on grammatical errors in sentences. Existing methods treat them as two separate tasks, sequence labeling, and conditional text generation respectively. As a consequence, a single encoder is typically selected as the backbone network to handle the CSC task whereas an encoder-decoder structure becomes a requisite for the CGEC task. However, in real-world applications, it is inefficient for a system to determine whether an input sentence contains spelling or grammatical errors and subsequently select different models according to the decision from the previous step. In this paper, to address these two tasks effectively, we propose a unified approach, denoted as UCSC-CGEC, based on a standard Transformer encoder-decoder structure. Notably, we choose to use a recent dataset named CSCD-IME instead of SIGHAN to ensure higher data quality in the CSC task. Additionally, to reduce the training difficulty and enhance generation quality, we introduce Copy Mechanism. Furthermore, to improve training efficiency and reduce cost, we adopt AdaLoRA, a Parameter-Efficient Fine-Tuning (PEFT) method, rather than fine-tuning the model with entire parameter set during the training phase. Experiments are conducted on CSCD-IME and NLPCC2018 datasets, and the results indicate the superiority of our approach when compared to all baseline models.

关键词： Chinese Spelling Check Chinese Grammatical Error Correction sequence-to-sequence model ParameterEfficient Fine-Tuning Copy Mechanism

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

Knowledge-based Questions Generation with Seq2Seq Learning 6

Knowledge-based Questions Generation with Seq2Seq Learning

引用

IEEE International Conference on Progress in Informatics and Computing (PIC)

作者： Tang, Xiangru Gao, Hanning Gao, Junjie Peking Univ Inst Comp Sci & Technol Beijing Peoples R China Cent China Normal Univ Sch Comp Wuhan Hubei Peoples R China

ISBN: (纸本)9781538676721

Building human-computer interaction engines is a fundamental challenge in Artificial Intelligence, with the goal of building a system which can automatically talk to human in natural language. Therefore, the ability to ask thought-provoking questions and contain valuable information in a conversational system is obviously quite crucial and challenging. In this paper, we build a knowledge-based question generation(KBQG) system which can generate natural language questions based on the given knowledge triples to demonstrate how large-scale knowledge base can facilitate language understanding and generation. We propose to apply the neural SEQ2SEQ learning model to generate meaningful questions from the given triples. The encoder reads in triples and produces an answer-aware input representation, which is fed to the decoder to generate an answer-focused question. To he able to express semantics completely and guarantee semantic integrity, we develop a flexible copy-attention mechanism that automatically replicates words from triples when needed. Both automatic and human evaluation results show that our model achieves outstanding performance. Furthermore, we establish a new evaluation metrics called GLAVE(Generated Language's automatic vector-pooling evaluation) to measure the similarity by pooling of word embeddings instead of word overlapping information, on account of the diversity and uncertainty of utterances. There are also a series of experiments which can demonstrate the effectiveness of our model is much stronger than state-of-the-art baselines.

关键词： language generation sequence-to-sequence model attention mechanism copynet Chinese knowledge graph

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：