检索结果-内蒙古大学图书馆

arXiv 2020年

作者： Hao, Changying Pang, Liang Lan, Yanyan Sun, Fei Guo, Jiafeng Cheng, Xueqi CAS Key Lab of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China Alibaba Group Beijing China

How to effectively utilize the dialogue history is a crucial problem in multi-turn dialogue generation. Previous works usually employ various neural network architectures (e.g., recurrent neural networks, attention mechanisms, and hierarchical structures) to model the history. However, a recent empirical study by Sankar et al. has shown that these architectures lack the ability of understanding and modeling the dynamics of the dialogue history. For example, the widely used architectures are insensitive to perturbations of the dialogue history, such as words shuffling, utterances missing, and utterances reordering. To tackle this problem, we propose a Ranking Enhanced Dialogue generation framework in this paper. Despite the traditional representation encoder and response generation modules, an additional ranking module is introduced to model the ranking relation between the former utterance and consecutive utterances. Specifically, the former utterance and consecutive utterances are treated as query and corresponding documents, and both local and global ranking losses are designed in the learning process. In this way, the dynamics in the dialogue history can be explicitly captured. To evaluate our proposed models, we conduct extensive experiments on three public datasets, i.e., bAbI, PersonaChat, and JDC. Experimental results show that our models produce better responses in terms of both quantitative measures and human judgments, as compared with the state-of-the-art dialogue generation models. Furthermore, we give some detailed experimental analysis to show where and how the improvements come from. Copyright © 2020, The Authors. All rights reserved.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Noise-Tolerant Learning for Audio-Visual Action Recognition

arXiv

引用

arXiv 2022年

作者： Han, Haochen Zheng, Qinghua Luo, Minnan Miao, Kaiyao Tian, Feng Chen, Yan The National Engineering Lab for Big Data Analytics Xi’an Jiaotong University Xi’an710049 China The School of Computer Science and Technology Xi’an Jiaotong University Xi’an710049 China The Key Laboratory of Intelligent Networks and Network Security Xi’an Jiaotong University Ministry of Education Xi’an710049 China The School of Cyber Science and Engineering Xi’an Jiaotong University Xi’an710049 China

Recently, video recognition is emerging with the help of multi-modal learning, which focuses on integrating distinct modalities to improve the performance or robustness of the model. Although various multi-modal learning methods have been proposed and offer remarkable recognition results, almost all of these methods rely on high-quality manual annotations and assume that modalities among multi-modal data provide semantically relevant information. Unfortunately, the widely used video datasets are usually coarse-annotated or collected from the Internet. Thus, it inevitably contains a portion of noisy labels and noisy correspondence. To address this challenge, we use the audio-visual action recognition task as a proxy and propose a noise-tolerant learning framework to find anti-interference model parameters against both noisy labels and noisy correspondence. Specifically, our method consists of two phases that aim to rectify noise by the inherent correlation between modalities. First, a noise-tolerant contrastive training phase is performed to make the model immune to the possible noisy-labeled data. Despite the benefits brought by contrastive training, it would overfit the noisy correspondence and thus provide false supervision. To alleviate the influence of noisy correspondence, we propose a cross-modal noise estimation component to adjust the consistency between different modalities. As the noisy correspondence existed at the instance level, we further propose a category-level contrastive loss to reduce its interference. Second, in the hybrid-supervised training phase, we calculate the distance metric among features to obtain corrected labels, which are used as complementary supervision to guide the training. Furthermore, due to the lack of suitable datasets, we establish a benchmark of real-world noisy correspondence in audio-visual data by relabeling the Kinetics dataset. Extensive experiments on a wide range of noisy levels demonstrate that our method significant

关键词： Modal analysis

来源：评论

学校读者我要写书评

暂无评论

Research on Knowledge Distillation of Generative Adversarial networks

Research on Knowledge Distillation of Generative Adversarial...

引用

data Compression Conference (DCC)

作者： Wei Wang Baohua Zhang Tao Cui Yimeng Chai Yue Li College of Computer Science KLMDASR Trusted AI System Lab Nankai University Tianjin China College of Computer Science Tianjin Key Lab of Network and Data Security Technology Nankai University Tianjin China NCMIS LSEC Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing China

The compression of Generative Adversarial networks (GANs) has been an emerging study in recent years. However, conventional compression methods can hardly be applied to GANs due to the training process and optimization target of GANs are different from the traditional classification detection network. Inspired by the recent success of knowledge distillation, we condense the recent researches on them applied to particular GANs, i.e. WGAN and CGAN for special tasks into two strategies: Soft Target Only Strategy (STOS) and Inherited Hard Target Strategy (IHTS), and propose an novel Random Hard Target Strategy, namely RHTS. In RHTS, we take the student network generator loss as the hard target of knowledge distillation when the discriminator is fixed, and the output of the teacher network generator as the soft target to distill GANs. The experiments on image datasets (MNIST, CIFAR-10), and structured-data datasets (Australian Credit Approval dataset, Credit Approval data Set) show that STOS and IHTS are effective, and RHTS is the best. Such results are further proved on WGAN, WGAN-GP and LSGAN in order to demonstrate the better generalization ability of the strategies. Besides, the RHTS improve the stability of the GAN training process, where the performance and stability confirm the rationality of our design.

关键词： Training Knowledge engineering data compression Generative adversarial networks Generators Task analysis Optimization

来源：评论

学校读者我要写书评

暂无评论

Better Pseudo-label: Joint Domain-aware label and Dual-classifier for Semi-supervised Domain Generalization

arXiv

引用

arXiv 2021年

作者： Wang, Ruiqi Qi, Lei Shi, Yinghuan Gao, Yang State Key Laboratory for Novel Software Technology Nanjing University Nanjing China National Institute of Healthcare Data Science Nanjing University Nanjing China School of Computer Science and Engineering Key Lab of Computer Network and Information Integration Ministry of Education Southeast University Nanjing China

With the goal of directly generalizing trained model to unseen target domains, domain generalization (DG), a newly proposed learning paradigm, has attracted considerable attention. Previous DG models usually require a sufficient quantity of annotated samples from observed source domains during training. In this paper, we relax this requirement about full annotation and investigate semisupervised domain generalization (SSDG) where only one source domain is fully annotated along with the other domains totally unlabeled in the training process. With the challenges of tackling the domain gap between observed source domains and predicting unseen target domains, we propose a novel deep framework via joint domain-aware labels and dual-classifier to produce high-quality pseudo-labels. Concretely, to predict accurate pseudo-labels under domain shift, a domain-aware pseudo-labeling module is developed. Also, considering inconsistent goals between generalization and pseudo-labeling: former prevents overfitting on all source domains while latter might overfit the unlabeled source domains for high accuracy, we employ a dual-classifier to independently perform pseudo-labeling and domain generalization in the training process. When accurate pseudo-labels are generated for unlabeled source domains, the domain mixup operation is applied to augment new domains between labeled and unlabeled domains, which is beneficial for boosting the generalization capability of the model. Extensive results on publicly available DG benchmark datasets show the efficacy of our proposed SSDG method. Copyright © 2021, The Authors. All rights reserved.

关键词： Image recognition

来源：评论

学校读者我要写书评

暂无评论

On the Relation between Quality-Diversity Evaluation and Distribution-Fitting Goal in Text Generation

arXiv

引用

arXiv 2020年

作者： Li, Jianing Lan, Yanyan Guo, Jiafeng Cheng, Xueqi CAS Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China

The goal of text generation models is to fit the underlying real probability distribution of text. For performance evaluation, quality and diversity metrics are usually applied. However, it is still not clear to what extend can the quality-diversity evaluation reflect the distribution-fitting goal. In this paper, we try to reveal such relation in a theoretical approach. We prove that under certain conditions, a linear combination of quality and diversity constitutes a divergence metric between the generated distribution and the real distribution. We also show that the commonly used BLEU/Self-BLEU metric pair fails to match any divergence metric, thus propose CR/NRR as a substitute for quality/diversity metric pair. Copyright © 2020, The Authors. All rights reserved.

关键词： Probability distributions

来源：评论

学校读者我要写书评

暂无评论

ICT at TREC 2019: Fair Ranking Track 28

ICT at TREC 2019: Fair Ranking Track

引用

28th Text REtrieval Conference, TREC 2019

作者： Wang, Meng Zhang, Haopeng Liang, Fuhuai Feng, Bin Zhao, Di CAS Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China

In this paper, we will introduce our work in the 2019 TREC fair ranking task. In temporal academic search, more and more people choose to pay attention to the fairness constraints of ranking. The purpose of this task is to provide fairness exposure to different groups of authors, where the definition of group is diverse, such as based on demographics, height, topics, etc. For this reason, the model we design should consider the fairness of the ranking results while ensuring the relevance of the ranking results. We will show how to use our model to achieve the relevance of query results, then adjust the overall ranking results according to the fairness of documents, and finally achieve the relevance and fairness of document ordering. This paper will introduce the framework and methods of the fair ranking system, as well as the experimental results. © 2019 28th Text REtrieval Conference, TREC 2019 - Proceedings. All Rights Reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Signal Feature Analysis of Contact Force at the Tip of a Flexible Ureteroscope 42

Signal Feature Analysis of Contact Force at the Tip of a Fle...

引用

42nd Annual International Conferences of the IEEE Engineering in Medicine and Biology Society, EMBC 2020

作者： Yinan, Deng Tangwen, Yang Shaotao, Dai Song, Guoli Beijing Jiaotong University Inst. of Info. Sci. and the Beijing Key Lab. of Advanced Information Science and Network Technology Beijing China Beijing Jiaotong University School of Electrical Engineering Beijing China Shenang Institute of Automation Cas State Key Laboratory of Robotics Shenyang China

ISBN: (纸本)9781728119908

This paper presents a signal analysis approach to identify the contact objects at the tip of a flexible ureteroscope. First, a miniature triaxial fiber optic sensor based on Fiber Bragg Grating(FBG) is devised to measure the interactive force signals at the ureteroscope tip. Due to the multidimensional properties of these force signals, the principal components analysis(PCA) method is introduced to reduce dimensions. The signal features are then extracted from the representative principal component signals using the wavelet transform(WT) method. Experimental results show that the contact objects at the tip of a ureteroscope are readily discriminated from the measured force signals with the proposed *** Relevance - This work commits to analyze the contact force signals at the tip of a flexible ureteroscope for the purpose of contact objects identification. © 2020 IEEE.

关键词： Fiber Bragg gratings

来源：评论

学校读者我要写书评

暂无评论

Optimization from Structured Samples for Coverage Functions

arXiv

引用

arXiv 2020年

作者： Chen, Wei Sun, Xiaoming Zhang, Jialin Zhang, Zhijie Microsoft Research Asia Beijing China CAS Key Lab of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China

We revisit the optimization from samples (OPS) model, which studies the problem of optimizing objective functions directly from the sample data. Previous results showed that we cannot obtain a constant approximation ratio for the maximum coverage problem using polynomially many independent samples of the form {Si, f (Si)}ti=1 (Balkanski et al., 2017), even if coverage functions are (1 − ǫ)-PMAC learnable using these samples (Badanidiyuru et al., 2012), which means most of the function values can be approximately learned very well with high probability. In this work, to circumvent the impossibility result of OPS, we propose a stronger model called optimization from structured samples (OPSS) for coverage functions, where the data samples encode the structural information of the functions. We show that under three general assumptions on the sample distributions, we can design efficient OPSS algorithms that achieve a constant approximation for the maximum coverage problem. We further prove a constant lower bound under these assumptions, which is tight when not considering computational efficiency. Moreover, we also show that if we remove any one of the three assumptions, OPSS for the maximum coverage problem has no constant approximation. Copyright © 2020, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Slimmable generative adversarial networks

arXiv

引用

arXiv 2020年

作者： Hou, Liang Yuan, Zehuan Huang, Lei Shen, Huawei Cheng, Xueqi Wang, Changhu CAS Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences University of Chinese Academy of Sciences ByteDance AI Lab SKLSDE Institute of Artificial Intelligence Beihang University

Generative adversarial networks (GANs) have achieved remarkable progress in recent years, but the continuously growing scale of models makes them challenging to deploy widely in practical applications. In particular, for real-time generation tasks, different devices require generators of different sizes due to varying computing power. In this paper, we introduce slimmable GANs (SlimGANs), which can flexibly switch the width of the generator to accommodate various quality-efficiency trade-offs at runtime. Specifically, we leverage multiple discriminators that share partial parameters to train the slimmable generator. To facilitate the consistency between generators of different widths, we present a stepwise inplace distillation technique that encourages narrow generators to learn from wide ones. As for class-conditional generation, we propose a sliceable conditional batch normalization that incorporates the label information into different widths. Our methods are validated, both quantitatively and qualitatively, by extensive experiments and a detailed ablation study. Copyright © 2020, The Authors. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

A Dual-Channel Framework for Sarcasm Recognition by Detecting Sentiment Conflict

arXiv

引用

arXiv 2021年

作者： Liu, Yiyi Wang, Yequan Sun, Aixin Meng, Xuying Li, Jing Guo, Jiafeng CAS Key Lab of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China Beijing Academy of Artificial Intelligence Beijing China School of Computer Science and Engineering Nanyang Technological University Singapore Singapore Institute of Computing Technology Chinese Academy of Sciences Beijing China Inception Institute of Artificial Intelligence Abu Dhabi United Arab Emirates

Sarcasm employs ambivalence, where one says something positive but actually means negative, and vice versa. The essence of sarcasm, which is also a sufficient and necessary condition, is the conflict between literal and implied sentiments expressed in one sentence. However, it is difficult to recognize such sentiment conflict because the sentiments are mixed or even implicit. As a result, the recognition of sophisticated and obscure sentiment brings in a great challenge to sarcasm detection. In this paper, we propose a Dual-Channel Framework by modeling both literal and implied sentiments separately. Based on this dual-channel framework, we design the Dual-Channel network (DC-Net) to recognize sentiment conflict. Experiments on political debates (i.e., IAC-V1 and IAC-V2) and Twitter datasets show that our proposed DC-Net achieves state-of-the-art performance on sarcasm recognition. Our code is released to support research https://***/yiyi-ict/dual-channel-for-sarcasm. © 2021, CC BY.

关键词：

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：