检索结果-内蒙古大学图书馆

4th International Conference on Computer Science and Computational Intelligence (ICCSCI) - Enabling Collaboration to Escalate Impact of Research Results for Society

作者： Chandra, Yogi Wisesa Suyanto, Suyanto Telkom Univ Sch Comp Jl Telekomunikasi 01 Terusan Buah Batu Bandung 40257 West Java Indonesia

Question and Answering (QA) system is a problem in natural language processing that can be used as the system of dialogs and chatbots. It can be used as a customer service that can provide a response to the customer quickly. A QA system receives an input in the form of sentences and produces the predictive sentences that are responses to the input. Therefore, a model that can learn such conversations is needed. This research focuses on developing a chatbot based on a sequence-to-sequence model. It is trained using a data set of conversation from a university admission. Evaluation on a small dataset obtained from the Telkom University admission on Whatsapp instant messaging application shows that the model produces a quite high BLEU score of 41.04. An attention mechanism technique using the reversed sentences improves the model to gives a higher BLEU up to 44.68. (C) 2019 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (http://***/licenses/by-nc-nd/4.0/) Peer-review under responsibility of the scientific committee of the 4th International Conference on Computer Science and Computational Intelligence 2019.

关键词： admission chatbot attention mechanism question-answering system sequence-to-sequence

来源：评论

学校读者我要写书评

暂无评论

Semi-supervised sequence-to-sequence ASR using Unpaired Speech and Text 20

Semi-supervised Sequence-to-sequence ASR using Unpaired Spee...

引用

Interspeech Conference

作者： Baskar, Murali Karthick Watanabe, Shinji Astudillo, Ramon Hori, Takaaki Burget, Lukas Cernocky, Jan Brno Univ Technol Brno Czech Republic Johns Hopkins Univ Baltimore MD 21218 USA IBM TJ Watson Res Ctr Yorktown Hts NY USA MERL Cambridge MA USA

sequence-to-sequence automatic speech recognition (ASR) models require large quantities of data to attain high performance. For this reason, there has been a recent surge in interest for unsupervised and semi-supervised training in such models. This work builds upon recent results showing notable improvements in semi-supervised training using cycle-consistency and related techniques. Such techniques derive training procedures and losses able to leverage unpaired speech and/or text data by combining ASR with Text-to-Speech (TTS) models. In particular, this work proposes a new semi-supervised loss combining an end-to-end differentiable ASR -> TTS loss with TTS -> ASR loss. The method is able to leverage both unpaired speech and text data to outperform recently proposed related techniques in terms of %WER. We provide extensive results analyzing the impact of data quantity and speech and text modalities and show consistent gains across WSJ and Librispeech corpora. Our code is provided in ESPnet to reproduce the experiments.

关键词： sequence-to-sequence end-to-end ASR TTS semi-supervised unsupervised cycle consistency

来源：评论

学校读者我要写书评

暂无评论

ATTS2S-VC: sequence-to-sequence VOICE CONVERSION WITH ATTENTION AND CONTEXT PRESERVATION MECHANISMS 44

ATTS2S-VC: SEQUENCE-TO-SEQUENCE VOICE CONVERSION WITH ATTENT...

引用

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

作者： Tanaka, Kou Kameoka, Hirokazu Kaneko, Takuhiro Hojo, Nobukatsu NTT Corp NTT Commun Sci Labs Tokyo Japan

ISBN: (纸本)9781479981311

This paper describes a method based on a sequence-to-sequence learning (Seq2Seq) with attention and context preservation mechanism for voice conversion (VC) tasks. Seq2Seq has been outstanding at numerous tasks involving sequence modeling such as speech synthesis and recognition, machine translation, and image captioning. In contrast to current VC techniques, our method 1) stabilizes and accelerates the training procedure by considering guided attention and proposed context preservation losses, 2) allows not only spectral envelopes but also fundamental frequency contours and durations of speech to be converted, 3) requires no context information such as phoneme labels, and 4) requires no time-aligned source and target speech data in advance. In our experiment, the proposed VC framework can be trained in only one day, using only one GPU of an NVIDIA Tesla K80, while the quality of the synthesized speech is higher than that of speech converted by Gaussian mixture model-based VC and is comparable to that of speech generated by recurrent neural network-based text-to-speech synthesis, which can be regarded as an upper limit on VC performance.

关键词： Voice conversion deep learning sequence-to-sequence attention mechanism context preservation mechanism

来源：评论

学校读者我要写书评

暂无评论

Estimating Power Consumption of Air-conditioners Using a sequence-to-sequence Model 9

Estimating Power Consumption of Air-conditioners Using a Seq...

引用

9th IEEE International Conference on Consumer Electronics (ICCE-Berlin)

作者： Hwang, Inhwan Cho, Hyeonje Ji, Yunhu Kim, Huijung Samsung Elect Co Ltd Samsung Res SR Seoul South Korea

ISBN: (纸本)9781728127453

We suggest a neural network based power estimation algorithm for air-conditioners exploiting a sequence-to-sequence model which is widely used in the field of natural language processing. Our proposed method exploits both past usage patterns and weather forecasts for better prediction because air-conditioners have high dependency on the environmental factors. Our proposed algorithm is trained and validated on real-world data collected in various regions of the Republic of Korea. For validation, we adopt two evaluation metrics, mean absolute error and mean absolute percentage error. We accordingly suggest two different types of accuracy metrics practical for end users. Applying the proposed method to real-world data from air-conditioners, we have 5.7 kW of mean absolute error and 23 percent of mean absolute percentage error. Accuracy out of each metric is 85.02 percent and 74.65 percent respectively which outperforms the conventional regression algorithms.

关键词： Air-conditioner Power consumption estimation Recurrent neural network sequence-to-sequence

来源：评论

学校读者我要写书评

暂无评论

Listen, Attend, Spell and Adapt: Speaker Adapted sequence-to-sequence ASR 20

Listen, Attend, Spell and Adapt: Speaker Adapted Sequence-to...

引用

Interspeech Conference

作者： Weninger, Felix Andres-Ferrer, Jesus Li, Xinwei Zhan, Puming Nuance Commun Inc Burlington MA 01803 USA Nuance Commun Inc Valencia Spain

sequence-to-sequence (seq2seq) based ASR systems have shown state-of-the-art performances while having clear advantages in terms of simplicity. However, comparisons are mostly done on speaker independent (SI) ASR systems, though speaker adapted conventional systems are commonly used in practice for improving robustness to speaker and environment variations. In this paper, we apply speaker adaptation to seq2seq models with the goal of matching the performance of conventional ASR adaptation. Specifically, we investigate Kullback-Leibler divergence (KLD) as well as Linear Hidden Network (LHN) based adaptation for seq2seq ASR, using different amounts (up to 20 hours) of adaptation data per speaker. Our SI models are trained on large amounts of dictation data and achieve state-of-the-art results. We obtained 25% relative word error rate (WER) improvement with KLD adaptation of the seq2seq model vs. 18.7% gain from acoustic model adaptation in the conventional system. We also show that the WER of the seq2seq model decreases log-linearly with the amount of adaptation data. Finally, we analyze adaptation based on the minimum WER criterion and adapting the language model (LM) for score fusion with the speaker adapted seq2seq model, which result in further improvements of the seq2seq system performance.

关键词： automatic speech recognition speaker adaptation sequence-to-sequence end-to-end

来源：评论

学校读者我要写书评

暂无评论

sequence-to-sequence Learning for Online Imputation of Sensory Data

引用

Instrumentation 2019年第2期6卷 63-70页

作者： Kaitai TONG Teng LI Faculty of Applied Science Uniwversity of British ColumbiaVancouwerBC V6T 1Z4Canada Department of Mechanical Engineering Unwversity of British ColumbiaVancouerBC V6T lZ4Canada

Online sensing can provide useful information in monitoring applications,for example,machine health monitoring,structural condition monitoring,environmental monitoring,and many *** data is generally a significant issue in the sensory data that is collected online by sensing systems,which may affect the goals of monitoring *** this paper,a sequence-to-sequence learning model based on a recurrent neural network(RNN)architecture is *** the proposed method,multivariate time series of the monitored parameters is embedded into the neural network through layer-by-layer encoders where the hidden features of the inputs are adaptively ***,predictions of the missing data are generated by network decoders,which are one-step-ahead predictive data sequences of the monitored *** prediction performance of the proposed model is validated based on a real-world sensory *** experimental results demonstrate the performance of the proposed RNN-encoder-decoder model with its capability in sequence-to-sequence learning for online imputation of sensory data.

关键词： Data Imputation Recurrent Neural Network sequence-to-sequence Learning sequence Prediction

来源：评论

学校读者我要写书评

暂无评论

Hierarchical sequence-to-sequence Model for Multi-Label Text Classification

引用

IEEE ACCESS 2019年 7卷 153012-153020页

作者： Yang, Zhenyu Liu, Guojing Qilu Univ Technol Sch Comp Sci & Technol ShanDong Acad Sci Jinan 250353 Shandong Peoples R China

We propose a novel sequence-to-sequence model for multi-label text classification, based on a parallel encoding, serial decoding strategy. The model combines a convolutional neural network and self-attention in parallel as the encoder to extract fine-grained local neighborhood information and global interaction information from the source text. We design a hierarchical decoder to decode and generate the label sequence. Our method not only gives full consideration to the interpretable fine-gained information in the source text but also effectively utilizes the information to generate the label sequence. We conducted a large number of comparative experiments on three datasets. The results show that the proposed model has significant advantages over the state-of-the-art baseline model. In addition, our analysis demonstrates that our model is competitive with the RNN-based Seq2Seq models and that it is more robust at handling datasets with a high label/sample ratio.

关键词： Decoding Task analysis Data mining Convolution Neural networks Encoding Analytical models sequence-to-sequence multi-label text classification self-attention hierarchical decoder attention mechanism

来源：评论

学校读者我要写书评

暂无评论

Intrusion Prediction With System-Call sequence-to-sequence Model

引用

IEEE ACCESS 2018年 6卷 71413-71421页

作者： Lv, Shaohua Wang, Jian Yang, Yinqi Liu, Jiqiang Beijing Jiaotong Univ Sch Comp & Informat Technol Beijing 100044 Peoples R China Beijing Jiaotong Univ Beijing Key Lab Secur & Privacy Intelligent Trans Beijing 100044 Peoples R China

The advanced development of the Internet facilitates efficient information exchange while also been exploited by adversaries. Intrusion detection system is an important defense component of network security that has always been widely studied in security research. However, the research of intrusion prediction, which is more critical for network security, received less attention. General research methods regarding prediction are analyzing short term of system-calls to predict forthcoming abnormal behaviors. However, those approaches have poor accuracy due to their limited sequence dependency. To solve this problem, in this paper, we take advantage of the remarkable performance of recurrent neural networks in dealing with long sequential problems, introducing the sequence-to-sequence model into our intrusion prediction work. By semantically modeling system-calls, we build a robust system-call sequence-to-sequence prediction model. Our prediction model predicts a sequence of system-calls that will be executed in the future, which will enable the monitoring of system state and the prediction of attack behavior. The experiments show that the prediction method proposed in this paper achieved well prediction performance on ADFA-LD intrusion detection test data set. Moreover, the predicted sequence, combined with the known invoked traces of system call, significantly improves the performance of intrusion detection verified on various classifiers.

关键词： Intrusion prediction anomaly intrusion detection recurrent neural networks sequence-to-sequence system-call

来源：评论

学校读者我要写书评

暂无评论

Indonesian Chatbot of University Admission Using a Question Answering System Based on sequence-to-sequence Model

引用

Procedia Computer Science 2019年 157卷 367-374页

作者： Yogi Wisesa Chandra Suyanto Suyanto School of Computing Telkom University Jl. Telekomunikasi No. 01 Terusan Buah Batu Bandung 40257 West Java Indonesia

关键词： admission chatbot attention mechanism question-answering system sequence-to-sequence

来源：评论

学校读者我要写书评

暂无评论

A sequence-to-sequence based Approach For the double Transliteration of Tunisian Dialect 4

A Sequence-to-Sequence based Approach For the double Transli...

引用

4th Annual International Conference on Arabic Computational Linguistics (ACLing)

作者： Younes, Jihene Souissi, Emna Achour, Hadhemi Ferchichi, Ahmed Univ Tunis ISGT LR99ES04 BESTMOD Le Bardo Tunisia Univ Tunis ENSIT Montfleury 1008 Tunisia

Transliteration consists of automatically transforming a grapheme's transcription from one writing system to another, while preserving its pronunciation. It is usually used in the context of machine translation and cross language information retrieval, mainly to deal with the issue of named entities and technical terms. In the case of some Arabic dialects, which are used on the social web in both Latin and Arabic scripts and which are still low-resource languages, transliteration is of great benefit for the automatic generation of various linguistic resources (parallel corpora and lexica), useful for their automatic processing. In this work, we focus on the Tunisian dialect transliteration. We propose a deep learning based sequence-to-sequence approach to perform a word-level transliteration of the user generated Tunisian dialect on the social web, in both Latin to Arabic and Arabic to Latin senses. (C) 2018 The Authors. Published by Elsevier B.V.

关键词： Tunsian dialect transliteration Latin transcription Arabic transcription sequence-to-sequence deep learning natural language processing

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：