检索结果-内蒙古大学图书馆

2023 World Wide Web Conference, WWW 2023

作者： Yang, Yuting Lei, Wenqiang Huang, Pei Cao, Juan Li, Jintao Chua, Tat-Seng Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences Beijing China Sichuan University Sichuan China Stanford University CA United States National University of Singapore Singapore Singapore

ISBN: (纸本)9781450394161

Dialogue State Tracking (DST) module is an essential component of task-oriented dialog systems to understand users' goals and needs. Collecting dialogue state labels including slots and values can be costly, requiring experts to annotate all (slot, value) information for each turn in dialogues. It is also difficult to define all possible slots and values in advance, especially with the wide application of dialogue systems in more and more new-rising applications. In this paper, we focus on improving DST module to generate dialogue states in circumstances with limited annotations and knowledge about slot ontology. To this end, we design a dual prompt learning framework for few-shot DST. The dual framework aims to explore how to utilize the language understanding and generation capabilities of pre-trained language models for DST efficiently. Specifically, we consider the learning of slot generation and value generation as dual tasks, and two kinds of prompts are designed based on this dual structure to incorporate task-related knowledge of these two tasks respectively. In this way, the DST task can be formulated as a language modeling task efficiently under few-shot settings. To evaluate the proposed framework, we conduct experiments on two task-oriented dialogue datasets. The results demonstrate that the proposed method not only outperforms existing state-of-the-art few-shot methods, but also can generate unseen slots. It indicates that DST-related knowledge can be probed from pre-trained language models and utilized to address low-resource DST efficiently with the help of prompt learning. © 2023 Owner/Author.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Glancing Future for Simultaneous Machine Translation

Glancing Future for Simultaneous Machine Translation

引用

International Conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Shoutao Guo Shaolei Zhang Yang Feng Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences (ICT/CAS) University of Chinese Academy of Sciences Beijing China

Simultaneous machine translation (SiMT) outputs translation while reading the source sentence. Unlike conventional sequence-to-sequence (seq2seq) training, existing SiMT methods adopt the prefix-to-prefix (prefix2prefix) training, where the model predicts target tokens based on partial source tokens. However, the prefix2prefix training diminishes the ability of the model to capture global information and introduces forced predictions due to the absence of essential source information. Consequently, it is crucial to bridge the gap between the prefix2prefix training and seq2seq training to enhance the translation capability of the SiMT model. In this paper, we propose a novel method that glances future in curriculum learning to achieve the transition from the seq2seq training to prefix2prefix training. Specifically, we gradually reduce the available source information from the whole sentence to the prefix corresponding to that latency. Our method is applicable to a wide range of SiMT methods and experiments demonstrate that our method outperforms strong baselines 1 .

关键词：

来源：评论

学校读者我要写书评

暂无评论

EmoDubber: Towards High Quality and Emotion Controllable Movie Dubbing

arXiv

引用

arXiv 2024年

作者： Cong, Gaoxiang Pan, Jiadong Li, Liang Qi, Yuankai Peng, Yuxin van den Hengel, Anton Yang, Jian Huang, Qingming Key Laboratory of Intelligent Information Processing Institute of Computing Technology CAS China Macquarie University Australia Peking University China University of Adelaide Australia

Given a piece of text, a video clip, and a reference audio, the movie dubbing task aims to generate speech that aligns with the video while cloning the desired voice. The existing methods have two primary deficiencies: (1) They struggle to simultaneously hold audio-visual sync and achieve clear pronunciation;(2) They lack the capacity to express user-defined emotions. To address these problems, we propose EmoDubber, an emotion-controllable dubbing architecture that allows users to specify emotion type and emotional intensity while satisfying high-quality lip sync and pronunciation. Specifically, we first design Lip-related Prosody Aligning (LPA), which focuses on learning the inherent consistency between lip motion and prosody variation by duration level contrastive learning to incorporate reasonable alignment. Then, we design Pronunciation Enhancing (PE) strategy to fuse the video-level phoneme sequences by efficient conformer to improve speech intelligibility. Next, the speaker identity adapting module aims to decode acoustics prior and inject the speaker style embedding. After that, the proposed Flow-based User Emotion Controlling (FUEC) is used to synthesize waveform by flow matching prediction network conditioned on acoustics prior. In this process, the FUEC determines the gradient direction and guidance scale based on the user’s emotion instructions by the positive and negative guidance mechanism, which focuses on amplifying the desired emotion while suppressing others. Extensive experimental results on three benchmark datasets demonstrate favorable performance compared to several state-of-the-art methods. Copyright © 2024, The Authors. All rights reserved.

关键词： Speech intelligibility

来源：评论

学校读者我要写书评

暂无评论

Uncertainty-Injected Cross-Domain Few-Shot Scene Classification From Remote Sensing Imagery

Uncertainty-Injected Cross-Domain Few-Shot Scene Classificat...

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Can Li He Chen Jiahao Li Yin Zhuang Liang Chen National Key Laboratory of Space-Born Intelligent Information Processing Beijing Institute of Technology Beijing China

ISBN: (数字)9798350360325

ISBN: (纸本)9798350360332

Cross-domain few-shot scene classification (CDFSSC) is crucial for remote sensing (RS) applications since it aims at transferring knowledge learned from the source domain to the target domain to facilitate the model’s few-shot classification for the target domain. However, existing methods ignored the feature statistic discrepancy caused by domain shifts, leading to an inferior performance on the target domain. In this paper, to facilitate the model’s adaptation of the domain shifts and achieve better cross-domain knowledge transfer, an uncertainty-injected cross-domain framework called UICD is proposed for CDFSSC tasks from RS imagery. First, a semi-supervised teacher-student structure is employed to achieve cross-domain knowledge transfer by conducting supervised learning on labeled source data and establishing consistent predictions on unlabeled target data. Secondly, uncertainty is injected in feature statistic modeling during cross-domain training to obtain more diverse feature statistics for data from both the source and target domains, which could promote the robustness and adaptation of the model to domain shifts, thus enabling the model to better adapt to unforeseen variations in the target domain. Extensive experiment results indicate the efficacy and superiority of the proposed methods.

关键词： Training Adaptation models Scene classification Uncertainty Supervised learning Data models Robustness

来源：评论

学校读者我要写书评

暂无评论

Improving Continual Few-shot Relation Extraction through Relational Knowledge Distillation and Prototype Augmentation 30

Improving Continual Few-shot Relation Extraction through Rel...

引用

Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024

作者： Zhang, Zhiheng Zeng, Daojian Bai, Xue Institute of AI and Targeted International Communication Hunan Normal University Changsha China Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing Hunan Normal University Changsha China Changsha Dworld AI Tech Co. Ltd. China

ISBN: (纸本)9782493814104

In this paper, we focus on the challenging yet practical problem of Continual Few-shot Relation Extraction (CFRE), which involves extracting relations in the continuous and iterative arrival of new data with only a few labeled examples. The main challenges in CFRE are overfitting due to few-shot learning and catastrophic forgetting caused by continual learning. To address these problems, we propose a novel framework called RK2DA, which seamlessly integrates prototype-based data augmentation and relational knowledge distillation. Specifically, RK2DA generates pseudo data by introducing Gaussian noise to the prototype embeddings and utilizes a novel two-phase multi-teacher relational knowledge distillation method to transfer diverse knowledge from different embedding spaces. Experimental results on the FewRel and TACRED datasets demonstrate that our method outperforms the state-of-the-art baselines. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

An End-to-End Autoencoder-based Probabilistic Shaping Method for Optical Communication 7

An End-to-End Autoencoder-based Probabilistic Shaping Method...

引用

7th Optics Young Scientist Summit, OYSS 2024

作者： Teng, Ziqiang Guo, Dong Gao, Ran Kong, Leyi Han, Wentao Chang, Huan Li, Zhipei Xin, Xiangjun School of Information and Electronics Beijing Institute of Technology 5 Zhongguancun South Street Haidian District Beijing100081 China National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing Beijing Institute of Technology 5 Zhongguancun South Street Haidian District Beijing100081 China Institute of Science and Technology Research Beijing Institute of Technology 5 Zhongguancun South Street Haidian District Beijing100081 China

ISBN: (数字)9781510688377

ISBN: (纸本)9781510688360

The advent of services such as big data and cloud computing has driven a continuous increase in the required transmission rate and capacity of optical fiber communication systems, which now support over 90% of global data traffic. Probability shaping (PS), which adjusts the probability distribution of constellation points, enhances both data transmission rates and the resilience of signals to channel nonlinearity. However, traditional PS methods, such as those using constant composition distribution matching (CCDM), cannot dynamically adjust the probability distribution of constellation points based on channel conditions. To address this limitation, we propose an end-to-end Autoencoder (AE)-based PS technique for optical communication. Simulation results show that compared to traditional 16/64/256QAM, this scheme achieves a maximum improvement of 0.356 bit/symbol in mutual information over the AWGN channel. In the optical fiber channel, under varying signal power and fiber length conditions, the mutual information is improved in different degrees and the influence of channel nonlinearity on the signal is reduced. Innovatively, residual connections are added to the decoder to enhance the model's generalization performance, enabling a deeper network structure and improving its ability to handle complex optical fiber channels. © 2025 SPIE.

关键词： Optical fiber communication

来源：评论

学校读者我要写书评

暂无评论

2023 7th International Conference on Communication and information Systems An Improved IOTA Protocol Based on Optimal Midway Walk 7

2023 7th International Conference on Communication and Infor...

引用

7th International Conference on Communication and information Systems, ICCIS 2023

作者： Wu, Hongcheng Zhi, Hui Liu, Yangyang Anhui University School of Electronic and Information Engineering Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Hefei230601 China Hefei Zhilian Technology Industry Investment Co. Ltd Hefei230601 China

ISBN: (纸本)9798350330540

IOTA (Internet of Things Applications) protocol aims to provide a secure and trustworthy protocol for realizing data-value interactions between IoT devices, and it has become the next possible direction for the development of Blockchain applications. IOTA protocol has the problem that the time-consuming cumulative weight update grows too fast with the increase of the number of transactions, this paper proposed an improved IOTA protocol based on optimal midway walk, the improved protocol uses cutting-edge transaction selection algorithm of weighted Monte Carlo Markov random walk to reduce cumulative weight update delay. Firstly, this improved IOTA protocol mainly ensures the efficiency of transaction confirmation without losing the security of consensus by introducing the optimal midway walk method, i.e., the starting point of each walk is chosen to depart at an optimal location. Secondly, this paper designs the indirect verification identity record algorithm and the layer degree of confirmation principle are designed to realize the improved IOTA protocol's resilience and resistance to Parasite chain attack. The experimental results show that the improved IOTA using random function to select the midway walk starting point from i-50λ, to i-75λsubstantially solves the system computational burden problem and greatly reduces the cumulative weight update delay. © 2023 IEEE.

关键词： cumulative weight IOTA midway walk Parasite chain attack

来源：评论

学校读者我要写书评

暂无评论

Pseudo-Centroid Representation Learning for Cross-domain Few-shot Classification from Remote Sensing Imagery

Pseudo-Centroid Representation Learning for Cross-domain Few...

引用

Signal, information and Data processing (ICSIDP), IEEE International Conference on

作者： Can Li Jianlin Xie He Chen Yin Zhuang Jiahao Li Liang Chen National Key Laboratory of Space-Born Intelligent Information Processing Beijing Institute of Technology Beijing China

ISBN: (数字)9798331515669

ISBN: (纸本)9798331515676

Cross-domain few-shot classification is gaining significant attention due to its potential to address challenges in remote sensing applications, such as large domain gaps and limited labeled data. Recent approaches have explored leveraging unlabeled target domain data for semi-supervised learning, in addition to source labeled data, to improve cross-domain training. However, these techniques often struggle with getting discriminative representation for distinguishing categories in novel target domains, particularly when facing new categories and limited training examples. To overcome these issues, we propose a novel cross-domain pseudo-centroid representation (CDPCR) framework, designed to generate more discriminative and adaptable class representations for improved cross-domain learning. The framework consists of a semi-supervised cross-domain structure that integrates both source labeled data and a portion of target unlabeled data to establish the relationship between domains. A consistency regularization branch is introduced to stabilize model outputs by aligning predictions on the target unlabeled data under input perturbations. Additionally, a pseudo-centroid contrastive representation learning module is incorporated to enhance intra-category feature consistency while improving the separability of inter-category representations, aiding the model in adapting to classification tasks across diverse domains. The effectiveness of the proposed CDPCR framework is validated through comprehensive experiments conducted across 8 cross-domain scenarios using remote sensing scene classification datasets.

关键词： Training Representation learning Adaptation models Scene classification Perturbation methods Semisupervised learning Predictive models Data processing Data models Remote sensing

来源：评论

学校读者我要写书评

暂无评论

Prediction of piRNA-mRNA interactions based on an interactive inference network

Prediction of piRNA-mRNA interactions based on an interactiv...

引用

2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023

作者： Liu, Yajun Li, Ru Li, Aimin Fei, Rong Guo, Xie Wu, Fang-Xiang Xi'an University of Technology Shaanxi Key Laboratory for Network Computing and Security Technology Xi'an China Xi'an University of Technology Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing Xi'an China University of Saskatchewan Division of Biomedical Engineering Department of Computer Science Department of Mechanical Engineering Saskatoon Canada

ISBN: (纸本)9798350337488

As the largest class of small non-coding RNAs, piRNAs primarily present in the reproductive cells of mammals, which influence post-transcriptional processes of mRNAs in multiple ways. Effective methods for predicting piRNA and mRNA target relationships can help identify piRNA functions, investigate the possibility of piRNAs as biomarkers and therapeutic targets. In this study, we propose a computational approach for classifying the relationships of piRNA-mRNA pairs based on an interactive inference network (IIN). First, we gather piRNA-mRNA target data, collect sequence data by position alignment, and construct a benchmark dataset. Furthermore, a reliable negative set is constructed by positive-unlabeled learning. Finally, we view a piRNA and a mRNA sequence as a premise and hypothesis sentence, respectively, and IIN model is used to predict the relationship between them. The experiments demonstrate that our method effectively characterizes piRNA-mRNA interaction and could be beneficial for researchers to investigate piRNA functions. © 2023 IEEE.

关键词： interactive inference network noncoding RNA piRNA-mRNA interactions positive-unlabeled learning

来源：评论

学校读者我要写书评

暂无评论

Learning to Localize Cross-Anatomy Landmarks in X-Ray Images with a Universal Model

引用

Biomedical Engineering Frontiers 2022年第1期3卷 298-308页

作者： Heqin Zhu Qingsong Yao Li Xiao S.Kevin Zhou Key Lab of Intelligent Information Processing of Chinese Academy of Sciences(CAS) Institute of Computing TechnologyCASBeijing 100190China Center for Medical Imaging RoboticsAnalytic Computing&Learning(MIRACLE)School of Biomedical Engineering&Suzhou Institute for Advanced ResearchUniversity of Science and Technology of ChinaSuzhou 215123China

Objective and Impact *** this work,we develop a universal anatomical landmark detection model which learns once from multiple datasets corresponding to different anatomical *** with the conventional model trained on a single dataset,this universal model not only is more light weighted and easier to train but also improves the accuracy of the anatomical landmark *** accurate and automatic localization of anatomical landmarks plays an essential role in medical image ***,recent deep learning-based methods only utilize limited data from a single *** is promising and desirable to build a model learned from different regions which harnesses the power of big *** model consists of a local network and a global network,which capture local features and global features,*** local network is a fully convolutional network built up with depth-wise separable convolutions,and the global network uses dilated convolution to enlarge the receptive field to model global *** evaluate our model on four 2D X-ray image datasets totaling 1710 images and 72 landmarks in four anatomical *** experimental results show that our model improves the detection accuracy compared to the state-of-the-art *** model makes the first attempt to train a single network on multiple datasets for landmark *** results qualitatively and quantitatively show that our proposed model performs better than other models trained on multiple datasets and even better than models trained on a single dataset separately.

关键词： convolution utilize separable

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：