检索结果-内蒙古大学图书馆

Machine translation using deep learning for universal networking language based on their structure

INTERNATIONAL JOURNAL OF MACHINE learning AND CYBERNETICS 2021年第8期12卷 2365-2376页

作者： Ali, Md. Nawab Yousuf Rahman, Md. Lizur Chaki, Jyotismita Dey, Nilanjan Santosh, K. C. East West Univ Dept Comp Sci & Engn Dhaka 1212 Bangladesh Vellore Inst Technol Sch Informat Technol & Engn Vellore Tamil Nadu India JIS Univ Dept Comp Sci & Engn Kolkata 700109 W Bengal India Univ South Dakota Comp Sci KCs PAMI Res Lab Vermillion SD 57069 USA

This paper presents a deep learning-based machine translation (MT) system that translates a sentence of subject-object-verb (SOV) structured language into subject-verb-object (SVO) structured language. This system uses recurrent neural networks (RNNs) and Encodings. Encode embedded RNNs generate a set of numbers from the input sentence, where the second RNNs generate the output from these sets of numbers. Three popular datasets of SOV structured language i.e., EMILLE corpus, Prothom-Alo corpus and Punjabi Monolingual Text Corpus ILCI-II are used as two different case-study to validate. In our experimental case-study 1, for the EMILLE corpus and Prothom-Alo corpus dataset, we have achieved 0.742, 4.11 and 0.18, respectively as Bilingual Evaluation Understudy (BLEU), NIST (metric) and tertiary entrance rank scores. Another case-study for Punjabi Monolingual Text Corpus ILCI-II dataset achieved a BLEU score of 0.75. Our results can be compared with the state-of-the-art results.

关键词： Machine translation Deep learning Recurrent neural network Encodings sequence-to-sequence learning

来源：评论

学校读者我要写书评

暂无评论

ConvS2S-VC: Fully Convolutional sequence-to-sequence Voice Conversion

引用

IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING 2020年 28卷 1849-1863页

作者： Kameoka, Hirokazu Tanaka, Kou Kwasny, Damian Kaneko, Takuhiro Hojo, Nobukatsu NTT Corp NTT Commun Sci Labs Atsugi Kanagawa 2430198 Japan

This article proposes a voice conversion (VC) method using sequence-to-sequence (seq2seq or S2S) learning, which flexibly converts not only the voice characteristics but also the pitch contour and duration of input speech. The proposed method, called ConvS2S-VC, has three key features. First, it uses a model with a fully convolutional architecture. This is particularly advantageous in that it is suitable for parallel computations using GPUs. It is also beneficial since it enables effective normalization techniques such as batch normalization to be used for all the hidden layers in the networks. Second, it achieves many-to-many conversion by simultaneously learning mappings among multiple speakers using only a single model instead of separately learning mappings between each speaker pair using a different model. This enables the model to fully utilize available training data collected from multiple speakers by capturing common latent features that can be shared across different speakers. Owing to this structure, our model works reasonably well even without source speaker information, thus making it able to handle any-to-many conversion tasks. Third, we introduce a mechanism, called the conditional batch normalization that switches batch normalization layers in accordance with the target speaker. This particular mechanism has been found to be extremely effective for our many-to-many conversion model. We conducted speaker identity conversion experiments and found that ConvS2S-VC obtained higher sound quality and speaker similarity than baseline methods. We also found from audio examples that it could perform well in various tasks including emotional expression conversion, electrolaryngeal speech enhancement, and English accent conversion.

关键词： Acoustics Training Computational modeling Task analysis Feature extraction Decoding Data models Attention fully convolutional model many-to-many VC sequence-to-sequence learning voice conversion (VC)

来源：评论

学校读者我要写书评

暂无评论

Neural Attention-Driven Non-Maximum Suppression for Person Detection

引用

IEEE TRANSACTIONS ON IMAGE PROCESSING 2023年 32卷 2454-2467页

作者： Symeonidis, Charalampos Mademlis, Ioannis Pitas, Ioannis Nikolaidis, Nikos Aristotle Univ Thessaloniki Dept Informat Thessaloniki 54124 Greece

Non-maximum suppression (NMS) is a post-processing step in almost every visual object detector. NMS aims to prune the number of overlapping detected candidate regions-of-interest (RoIs) on an image, in order to assign a single and spatially accurate detection to each object. The default NMS algorithm (GreedyNMS) is fairly simple and suffers from severe drawbacks, due to its need for manual tuning. A typical case of failure with high application relevance is pedestrian/person detection in the presence of occlusions, where GreedyNMS doesn't provide accurate results. This paper proposes an efficient deep neural architecture for NMS in the person detection scenario, by capturing relations of neighboring RoIs and aiming to ideally assign precisely one detection per person. The presented Seq2Seq-NMS architecture assumes a sequence-to-sequence formulation of the NMS problem, exploits the Multihead Scale-Dot Product Attention mechanism and jointly processes both geometric and visual properties of the input candidate RoIs. Thorough experimental evaluation on three public person detection datasets shows favourable results against competing methods, with acceptable inference runtime requirements.

关键词： Detectors Object detection Visualization Task analysis Training Proposals Object recognition Non-maximum suppression object detection scaled-dot product attention sequence-to-sequence learning person detection deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Many-to-Many Voice Transformer Network

引用

IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING 2021年 29卷 656-670页

作者： Kameoka, Hirokazu Huang, Wen-Chin Tanaka, Kou Kaneko, Takuhiro Hojo, Nobukatsu Toda, Tomoki NTT Corp NTT Commun Sci Labs Atsugi Kanagawa 2430198 Japan Nagoya Univ Nagoya Aichi 4648601 Japan

This paper proposes a voice conversion (VC) method based on a sequence-to-sequence (S2S) learning framework, which enables simultaneous conversion of the voice characteristics, pitch contour, and duration of input speech. We previously proposed an S2S-based VC method using a transformer network architecture called the voice transformer network (VTN). The original VTN was designed to learn only a mapping of speech feature sequences from one speaker to another. Here, the main idea we propose is an extension of the original VTN that can simultaneously learn mappings among multiple speakers. This extension, called the many-to-many VTN, enables us to fully use available training data collected from multiple speakers by capturing common latent features that can be shared across different speakers. It also allows us to introduce a training loss called the identity mapping loss to ensure that the input feature sequence will remain unchanged when the source and target speaker indices are the same. Using this particular loss for model training has been found to be extremely effective in improving the performance of the model at test time. We conducted speaker identity conversion experiments and found that our model obtained higher sound quality and speaker similarity than baseline methods. We also found that our model, with a slight modification to its architecture, can handle any-to-many conversion tasks reasonably well.

关键词： Training Acoustics Computational modeling Decoding Data models Training data Computer architecture Attention many-to-many VC sequence-to-sequence learning voice conversion (VC) transformer network

来源：评论

学校读者我要写书评

暂无评论

Product review summarization through question retrieval and diversification

引用

INFORMATION RETRIEVAL JOURNAL 2017年第6期20卷 575-605页

作者： Liu, Mengwen Fang, Yi Choulos, Alexander G. Park, Dae Hoon Hu, Xiaohua Drexel Univ Philadelphia PA 19104 USA Santa Clara Univ Santa Clara CA 95053 USA Huawei Res Amer Santa Clara CA USA

Product reviews have become an important resource for customers before they make purchase decisions. However, the abundance of reviews makes it difficult for customers to digest them and make informed choices. In our study, we aim to help customers who want to quickly capture the main idea of a lengthy product review before they read the details. In contrast with existing work on review analysis and document summarization, we aim to retrieve a set of real-world user questions to summarize a review. In this way, users would know what questions a given review can address and they may further read the review only if they have similar questions about the product. Specifically, we design a two-stage approach which consists of question selection and question diversification. For question selection phase, we first employ probabilistic retrieval models to locate candidate questions that are relevant to a given review. A Recurrent Neural Network Encoder-Decoder is utilized to measure the "answerability" of questions to a review. We then design a set function to re-rank the questions with the goal of rewarding diversity in the final question set. The set function satisfies submodularity and monotonicity, which results in an efficient greedy algorithm of submodular optimization. Evaluation on product reviews from two categories shows that the proposed approach is effective for discovering meaningful questions that are representative of individual reviews.

关键词： Review summarization Question retrieval sequence-to-sequence learning Diversity

来源：评论

学校读者我要写书评

暂无评论

Topic-to-Text Generation with PMI-IR Additional Semantic Information

Topic-to-Text Generation with PMI-IR Additional Semantic Inf...

引用

25th International Conference on Asian Language Processing (IALP)

作者： Ning, Xinyi Beijing Univ Posts & Telecommun Dept Int Beijing Peoples R China

ISBN: (纸本)9781665483117

The purpose of this paper is to study the use of a deep learning method to make a machine automatically generate coherent text related to a topic based on user-specified multiple topic words. The existing research on topic-to-essay generation is mainly based on the topic words inputted by users, but the result of model generation is not satisfactory due to the limited semantic information of the subject words that can be obtained from the input. To solve this problem, this paper proposes a topic-to-essay generation model (PMI-IR similarity model) based on the corpus of keywords with additional semantic information. According to the similarity relationship between the input subject words and corpus words, this paper designed and constructed a corpus-based PMI-IR similarity computing similarity network. In the process of generation, the words with high similarity to the input topic words are selected as additional semantic information to be introduced into the model. This model is superior to the existing models in both manual evaluation and BLEU automatic evaluation. The text paragraphs generated by the model are closer to the topic, and the generated text paragraphs are more fluent and coherent.

关键词： Topic-to-essay generation PMI-IR LSTM sequence-to-sequence learning

来源：评论

学校读者我要写书评

暂无评论

Graph-in-Graph Network for Automatic Gene Ontology Description Generation 22

Graph-in-Graph Network for Automatic Gene Ontology Descripti...

引用

28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KKD)

作者： Liu, Fenglin Yang, Bang You, Chenyu Wu, Xian Ge, Shen Woicik, Adelaide Wang, Sheng Peking Univ Sch ECE Beijing Peoples R China Yale Univ Dept Elect Engn New Haven CT USA Tencent Jarvis Lab Beijing Peoples R China Univ Washington Paul G Allen Sch Comp Sci Seattle WA 98195 USA

ISBN: (纸本)9781450393850

Gene Ontology (GO) is the primary gene function knowledge base that enables computational tasks in biomedicine. The basic element of GO is a term, which includes a set of genes with the same function. Existing research efforts of GO mainly focus on predicting gene term associations. Other tasks, such as generating descriptions of new terms, are rarely pursued. In this paper, we propose a novel task: GO term description generation. This task aims to automatically generate a sentence that describes the function of a GO term belonging to one of the three categories, i.e., molecular function, biological process, and cellular component. To address this task, we propose a Graph-in-Graph network that can efficiently leverage the structural information of GO. The proposed network introduces a two-layer graph: the first layer is a graph of GO terms where each node is also a graph (gene graph). Such a Graph-in-Graph network can derive the biological functions of GO terms and generate proper descriptions. To validate the effectiveness of the proposed network, we build three large-scale benchmark datasets. By incorporating the proposed Graph-in-Graph network, the performances of seven different sequence-to-sequence models can be substantially boosted across all evaluation metrics, with up to 34.7%, 14.5%, and 39.1% relative improvements in BLEU, ROUGE-L, and METEOR, respectively.

关键词： Bioinformatics Gene Ontology Natural Language Generation Graph Representations sequence-to-sequence learning

来源：评论

学校读者我要写书评

暂无评论

Retrospective Encoders for Video Summarization 15th

Retrospective Encoders for Video Summarization

引用

15th European Conference on Computer Vision (ECCV)

作者： Zhang, Ke Grauman, Kristen Sha, Fei Univ Southern Calif Dept Comp Sci Los Angeles CA 90089 USA Facebook AI Res 300 W Sixth St Austin TX 78701 USA Netflix 5808 Sunset Blvd Los Angeles CA 90028 USA

ISBN: (纸本)9783030012373;9783030012366

Supervised learning techniques have shown substantial progress on video summarization. State-of-the-art approaches mostly regard the predicted summary and the human summary as two sequences (sets), and minimize discriminative losses that measure element-wise discrepancy. Such training objectives do not explicitly model how well the predicted summary preserves semantic information in the video. Moreover, those methods often demand a large amount of human generated summaries. In this paper, we propose a novel sequence-to-sequence learning model to address these deficiencies. The key idea is to complement the discriminative losses with another loss which measures if the predicted summary preserves the same information as in the original video. To this end, we propose to augment standard sequence learning models with an additional "retrospective encoder" that embeds the predicted summary into an abstract semantic space. The embedding is then compared to the embedding of the original video in the same space. The intuition is that both embeddings ought to be close to each other for a video and its corresponding summary. Thus our approach adds to the discriminative loss a metric learning loss that minimizes the distance between such pairs while maximizing the distances between unmatched ones. One important advantage is that the metric learning loss readily allows learning from videos without human generated summaries. Extensive experimental results show that our model outperforms existing ones by a large margin in both supervised and semi-supervised settings.

关键词： Video summarization sequence-to-sequence learning

来源：评论

学校读者我要写书评

暂无评论

MERCURY: An Automated Remote Side-channel Attack to Nvidia Deep learning Accelerator 22

MERCURY: An Automated Remote Side-channel Attack to Nvidia D...

引用

22nd International Conference on Field Programmable Technology (ICFPT)

作者： Yan, Xiaobei Lou, Xiaoxuan Xu, Guowen Qiu, Han Guo, Shangwei Chang, Chip Hong Zhang, Tianwei Nanyang Technol Univ Singapore Singapore City Univ Hong Kong Hong Kong Peoples R China Tsinghua Univ Beijing Peoples R China Chongqing Univ Chongqing Peoples R China

ISBN: (纸本)9798350359114

DNN accelerators have been widely deployed in many scenarios to speed up the inference process and reduce the energy consumption. One big concern about the usage of the accelerators is the confidentiality of the deployed models: model inference execution on the accelerators could leak side-channel information, which enables an adversary to preciously recover the model details. Such model extraction attacks can not only compromise the intellectual property of DNN models, but also facilitate some adversarial attacks. Although previous works have demonstrated a number of side-channel techniques to extract models from DNN accelerators, they are not practical for two reasons. (1) They only target simplified accelerator implementations, which have limited practicality in the real world. (2) They require heavy human analysis and domain knowledge. To overcome these limitations, this paper presents MERCURY, the first automated remote side-channel attack against the off-the-shelf Nvidia DNN accelerator. The key insight of MERCURY is to model the side-channel extraction process as a sequence-to-sequence problem. The adversary can leverage a time-to-digital converter (TDC) to remotely collect the power trace of the target model's inference. Then he uses a learning model to automatically recover the architecture details of the victim model from the power trace without any prior knowledge. The adversary can further use the attention mechanism to localize the leakage points that contribute most to the attack. Evaluation results indicate that MERCURY can keep the error rate of model extraction below 1%.

关键词： profiled side-channel attacks DNN accelerator sequence-to-sequence learning FPGA model extraction

来源：评论

学校读者我要写书评

暂无评论

Generating Mobility Trajectories with Retained Data Utility 21

Generating Mobility Trajectories with Retained Data Utility

引用

27th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD)

作者： Cao, Chu Li, Mo Nanyang Technol Univ Singapore Singapore

ISBN: (纸本)9781450383325

This paper presents TrajGen, an approach to generate artificial datasets of mobility trajectories based on an original trajectory dataset while retaining the utility of the original data in supporting various mobility applications. The generated mobility data is disentangled with the original data and can be shared without compromising the data privacy. TrajGen leverages Generative Adversarial Nets combined with a Seq2Seq model to generate the spatial-temporal trajectory data. TrajGen is implemented and evaluated with real-world taxi trajectory data in Singapore. The extensive experimental results demonstrate that TrajGen is able to generate artificial trajectory data that retain key statistical characteristics of the original data. Two case studies, i.e., road map updating and Origin-Destination dentarid estimation are performed with the generated artificial data, and the results show that the artificial trajectories generated by TrajGen retain the utility of original data in supporting the two applications.

关键词： Mobility Trajectories Generating Data Utility Generative Adversarial Nets sequence-to-sequence learning

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：