检索结果-内蒙古大学图书馆

Intelligent Systems Conference (IntelliSys)

作者： Fouad, Mohammed M. Mahany, Ahmed Katib, Iyad Fujitsu Technol Solut Jeddah Saudi Arabia Ain Shams Univ Cairo Egypt King Abdulaziz Univ Jeddah Saudi Arabia

ISBN: (纸本)9783030295134;9783030295127

Preprocessing the input textual data is the main starting step in any Natural Language Processing (NLP) application. Word stemming, i.e. extracting the stem or root of the input word, is a vital process within the preprocessing step. In this process, some words like "player", "playing", and "played" are mapped to their stem "play". In the English language, there are several algorithms and approaches that can be applied directly to handle this process. On the other hand, there are some trials for similar algorithms in Arabic, but all have weak performance due to the complexity of the language and the approaches used for building such algorithms. In this paper, we presented a novel deep learning-based model, called Masdar, for Arabic stemming. The proposed model leverages the power of the deep learning, especially the recurrent neural networks, in building an efficient Arabic stemmer that is capable of producing very accurate stems for most of the input words. Some experiments are conducted to compare the performance of the proposed model with the latest cited Arabic stemmers on a dataset of about 6000 Arabic word/stem pairs. The experimental results show that Masder outperformed the other stemmers. It can efficiently produce the correct stems with about 95% accuracy on the whole dataset and about 82% accuracy on the unseen test words.

关键词： Masdar Natural Language Processing Deep learning Recurrent Neural Network sequence-to-sequence Arabic stemmer

来源：评论

学校读者我要写书评

暂无评论

SCALABLE SENTIMENT FOR sequence-to-sequence CHATBOT RESPONSE WITH PERFORMANCE ANALYSIS

SCALABLE SENTIMENT FOR SEQUENCE-TO-SEQUENCE CHATBOT RESPONSE...

引用

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

作者： Lee, Chih-Wei Wang, Yau-Shian Hsu, Tsung-Yuan Chen, Kuan-Yu Lee, Hung-Yi Lee, Lin-Shan Natl Taiwan Univ Grad Inst Commun Engn Taipei Taiwan

ISBN: (纸本)9781538646588

Conventional seq2seq chatbot models only try to find the sentences with the highest probabilities conditioned on the input sequences, without considering the sentiment of the output sentences. Some research works trying to modify the sentiment of the output sequences were reported. In this paper, we propose five models to scale or adjust the sentiment of the chatbot response: persona-based model, reinforcement learning, plug and play model, sentiment transformation network and cycleGAN, all based on the conventional seq2seq model. We also develop two evaluation metrics to estimate if the responses are reasonable given the input. These metrics together with other two popularly used metrics were used to analyze the performance of the five proposed models on different aspects, and reinforcement learning and cycleGAN were shown to be very attractive. The evaluation metrics were also found to be well correlated with human evaluation.

关键词： chatbot dialogue sequence-to-sequence style-transfer response generation

来源：评论

学校读者我要写书评

暂无评论

IMPROVING sequence-to-sequence SPEECH RECOGNITION TRAINING WITH ON-THE-FLY DATA AUGMENTATION

IMPROVING SEQUENCE-TO-SEQUENCE SPEECH RECOGNITION TRAINING W...

引用

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

作者： Nguyen, Thai-Son Stuker, Sebastian Niehues, Jan Waibel, Alex Karlsruhe Inst Technol Inst Anthropomat & Robot Karlsruhe Germany Maastricht Univ Dept Data Sci & Knowledge Engn DKE Maastricht Netherlands

ISBN: (纸本)9781509066315

sequence-to-sequence (S2S) models recently started to show state-of-the-art performance for automatic speech recognition (ASR). With these large and deep models overfitting remains the largest problem, outweighing performance improvements that can be obtained from better architectures. One solution to the overfitting problem is increasing the amount of available training data and the variety exhibited by the training data with the help of data augmentation. In this paper we examine the influence of three data augmentation methods on the performance of two S2S model architectures. One of the data augmentation method comes from literature, while two other methods are our own development - a time perturbation in the frequency domain and sub-sequence sampling. Our experiments on Switchboard and Fisher data show state-of-the-art performance for S2S models that are trained solely on the speech training data and do not use additional text data.

关键词： sequence-to-sequence Self-attention Data Augmentation Speed Perturbation Sub-sequence

来源：评论

学校读者我要写书评

暂无评论

A Realistic Drum Accompaniment Generator Using sequence-to-sequence Model and MIDI Music Database 30

A Realistic Drum Accompaniment Generator Using Sequence-to-S...

引用

30th IEEE Signal Processing and Communications Applications Conference (SIU)

作者： Akyuz, Yavuz Batuhan Gumustekin, Sevket Izmir Yuksek Teknol Enstitusu Elekt Elekt Muhendisligi TR-35430 Urla Izmir Turkiye

ISBN: (纸本)9781665450928

In this work, artificial intelligence reinterpretation and/or addition of drum parts for musical pieces supplied in Musical Instruments Digital Interface (MIDI) format, have been carried out. To achieve this, sequence-to-sequence learning method and Encoder-Decoder Long Short-Term Memory (LSTM) artificial neural network model have been used. In order to improve training of this neural network, teacher forcing method was utilized. In the generation of new drum parts, the quality and the originality of the samples were improved by using temperature sampling. Our proposed method produces high quality drum accompaniments with adjustable complexity.

关键词： MIDI sequence-to-sequence encoder and decoder long-short term memory teacher forcing temperature sampling autonomous music accompany

来源：评论

学校读者我要写书评

暂无评论

SPEECH-TRANSFORMER: A NO-RECURRENCE sequence-to-sequence MODEL FOR SPEECH RECOGNITION

SPEECH-TRANSFORMER: A NO-RECURRENCE SEQUENCE-TO-SEQUENCE MOD...

引用

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

作者： Dong, Linhao Xu, Shuang Xu, Bo Chinese Acad Sci Inst Automat Beijing Peoples R China Univ Chinese Acad Sci Beijing Peoples R China

ISBN: (纸本)9781538646588

Recurrent sequence-to-sequence models using encoder-decoder architecture have made great progress in speech recognition task. However, they suffer from the drawback of slow training speed because the internal recurrence limits the training parallelization. In this paper, we present the Speech-Transformer, a no-recurrence sequence-to-sequence model entirely relies on attention mechanisms to learn the positional dependencies, which can be trained faster with more efficiency. We also propose a 2D-Attention mechanism, which can jointly attend to the time and frequency axes of the 2-dimensional speech inputs, thus providing more expressive representations for the Speech-Transformer. Evaluated on the Wall Street Journal (WSJ) speech recognition dataset, our best model achieves competitive word error rate (WER) of 10.9%, while the whole training process only takes 1.2 days on 1 GPU, significantly faster than the published results of recurrent sequence-to-sequence models.

关键词： Speech Recognition sequence-to-sequence Attention Transformer

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

Une alternative aux modèles neuronaux séquence-à-séquence pour la traduction automatique: Rethinking the Design of sequence-to-sequence Models for Efficient Machine Translation

Une alternative aux modèles neuronaux séquence-à-séquenc...

引用

作者： Elbayad, Maha Université Grenoble Alpes

学位级别：博士

L'apprentissage profond a permis des avancées significatives dans le domaine de la traduction *** traduction automatique neuronale (NMT) s'appuie sur l'entrainement de réseaux de neurones avec un grand nombre de paramètres sur une grand quantité de données parallèles pour apprendre à traduire d'une langue à une *** facteur primordial dans le succès des systèmes NMT est la capacité de concevoir des architectures puissantes et efficaces. Les systèmes de pointe sont des modèles encodeur-décodeurs qui, d'abord, encodent une séquence source sous forme de vecteurs de caractéristiques, puis décodent de façon conditionne la séquence *** cette thèse, nous remettons en question le paradigme encodeur-décodeur et préconisons de conjointement encoder la source et la cible afin que les deux séquences interagissent à des niveaux d'abstraction croissants. À cette fin, nous introduisons Pervasive Attention, un modèle basé sur des convolutions bidimensionnelles qui encodent conjointement les séquences source et cible avec des interactions qui sont omniprésentes dans le réseau *** améliorer l'efficacité des systèmes NMT, nous étudions la traduction automatique simultanée où la source est lue de manière incrémentielle et le décodeur est alimenté en contextes partiels afin que le modèle puisse alterner entre lecture et écriture. Nous améliorons les agents déterministes qui guident l'alternance lecture / écriture à travers un chemin de décodage rigide et introduisons de nouveaux agents dynamiques pour estimer un chemin de décodage adapté au *** abordons également l'efficacité computationnelle des modèles NMT et affirmons qu'ajouter plus de couches à un réseau de neurones n'est pas requis pour tous les *** concevons des décodeurs Transformer qui peuvent émettre des prédictions à tout moment dotés de mécanismes d'arrêt adaptatifs pour allouer des ressources en fonction de la complexité de l'instance. In recent years, deep learning has enab

关键词： Apprentissage profond Traduction automatique Séquence-À-Séquence Réseaux à convolution Mécanisme d'attention Deep learning Machine translation sequence-to-sequence Convolutional neural networks Attention mechanims 004

来源：评论

学校读者我要写书评

暂无评论

RASR2: The RWTH ASR Toolkit for Generic sequence-to-sequence Speech Recognition 24

RASR2: The RWTH ASR Toolkit for Generic Sequence-to-sequence...

引用

Interspeech Conference

作者： Zhou, Wei Beck, Eugen Berger, Simon Schlueter, Ralf Ney, Hermann Rhein Westfal TH Aachen Dept Comp Sci Machine Learning & Human Language Technol D-52074 Aachen Germany AppTek GmbH D-52062 Aachen Germany

Modern public ASR tools usually provide rich support for training various sequence-to-sequence (S2S) models, but rather simple support for decoding open-vocabulary scenarios only. For closed-vocabulary scenarios, public tools supporting lexical-constrained decoding are usually only for classical ASR, or do not support all S2S models. To eliminate this restriction on research possibilities such as modeling unit choice, we present RASR2 in this work, a research-oriented generic S2S decoder implemented in C++. It offers a strong flexibility/compatibility for various S2S models, language models, label units/topologies and neural network architectures. It provides efficient decoding for both open- and closed-vocabulary scenarios based on a generalized search framework with rich support for different search modes and settings. We evaluate RASR2 with a wide range of experiments on both switchboard and Librispeech corpora. Our source code is public online.

关键词： speech recognition toolkit sequence-to-sequence decoder beam search RASR

来源：评论

学校读者我要写书评

暂无评论

SPT-Code: sequence-to-sequence Pre-Training for Learning Source Code Representations 22

SPT-Code: Sequence-to-Sequence Pre-Training for Learning Sou...

引用

ACM/IEEE 44th International Conference on Software Engineering (ICSE)

作者： Niu, Changan Li, Chuanyi Ng, Vincent Ge, Jidong Huang, Liguo Luo, Bin Nanjing Univ State Key Lab Novel Software Technol Nanjing Peoples R China Univ Texas Dallas Human Language Technol Res Inst Richardson TX 75083 USA Southern Methodist Univ Dept Comp Sci Dallas TX USA

ISBN: (纸本)9781450392211

Recent years have seen the successful application of large pretrained models to code representation learning, resulting in substantial improvements on many code-related downstream tasks. But there are issues surrounding their application to SE tasks. First, the majority of the pre-trained models focus on pre-training only the encoder of the Transformer. For generation tasks that are addressed using models with the encoder-decoder architecture, however, there is no reason why the decoder should be left out during pre-training. Second, many existing pre-trained models, including state-of-the-art models such as T5-learning, simply reuse the pretraining tasks designed for natural languages. Moreover, to learn the natural language description of source code needed eventually for code-related tasks such as code summarization, existing pretraining tasks require a bilingual corpus composed of source code and the associated natural language description, which severely limits the amount of data for pre-training. To this end, we propose SPT-Code, a sequence-to-sequence pre-trained model for source code. In order to pre-train SPT-Code in a sequence-to-sequence manner and address the aforementioned weaknesses associated with existing pre-training tasks, we introduce three pre-training tasks that are specifically designed to enable SPT-Code to learn knowledge of source code, the corresponding code structure, as well as a natural language description of the code without relying on any bilingual corpus, and eventually exploit these three sources of information when it is applied to downstream tasks. Experimental results demonstrate that SPT-Code achieves state-of-the-art performance on five code-related downstream tasks after fine-tuning.

关键词： pre-training code representation learning sequence-to-sequence

来源：评论

学校读者我要写书评

暂无评论

Syllable-Based sequence-to-sequence Speech Recognition with the Transformer in Mandarin Chinese 19

Syllable-Based Sequence-to-Sequence Speech Recognition with ...

引用

19th Annual Conference of the International-Speech-Communication-Association (INTERSPEECH 2018)

作者： Zhou, Shiyu Dong, Linhao Xu, Shuang Xu, Bo Chinese Acad Sci Inst Automat Beijing Peoples R China Univ Chinese Acad Sci Beijing Peoples R China

ISBN: (纸本)9781510872219

sequence-to-sequence attention-based models have recently shown very promising results on automatic speech recognition (ASR) tasks, which integrate an acoustic, pronunciation and language model into a single neural network. In these models, the Transformer, a new sequence-to-sequence attention based model relying entirely on self-attention without using RNNs or convolutions, achieves a new single-model state-of-the-art BLEU on neural machine translation (NMT) tasks. Since the outstanding performance of the Transformer, we extend it to speech and concentrate on it as the basic architecture of sequence-to-sequence attention-based model on Mandarin Chinese ASR tasks. Furthermore, we investigate a comparison between syllable based model and context-independent phoneme (CI-phoneme) based model with the Transformer in Mandarin Chinese. Additionally, a greedy cascading decoder with the Transformer is proposed for mapping CI-phoneme sequences and syllable sequences into word sequences. Experiments on HKUST datasets demonstrate that syllable based model with the Transformer performs better than CI-phoneme based counterpart, and achieves a character error rate (CER) of 28.77%, which is competitive to the state-of-the-art CER of 28.0% by the joint CTC-attention based encoder-decoder network.

关键词： ASR multi-head attention syllable based acoustic modeling sequence-to-sequence

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：