检索结果-内蒙古大学图书馆

A k-Nearest-Neighbor Machine Translation Method Combining Certainty Factor and Region Density 23

23rd Chinese National Conference on Computational Linguistics, CCL 2024

作者： Qi, Rui Shi, Xiangyu Man, Zhibo Xu, Jinan Chen, Yufeng Beijing Jiaotong University School of Computer Science and Technology Beijing100044 China Beijing Key Lab of Traffic Data Analysis and Mining Beijing100044 China

ISBN: (纸本)9780000000002

k-Nearest-Neighbor Machine Translation (kNN-MT) is an important research direction in the field of neural machine translation in recent years. It can improve the translation quality without updating the model, but there are still many problems to be solved: the number of each label in training data is not balanced, and the fixed k value can not produce good translation results for the data in different density regions. In this paper, we propose an innovative KNN-MT method to reduce the influence of imbalanced dataset by introducing a certainty factor (CF), and to optimize the search effect by adjusting the k value dynamically according to the data density around the test point. On the multi-domain German-English translation dataset, compared with the baseline experiment, our method has improved the translation performance in all four domains, three of which have improved by more than 1 BLEU. © 2024 China National Conference on Computational Linguistics.

关键词： Nearest neighbor search

来源：评论

学校读者我要写书评

暂无评论

Language-assisted Vision Model Debugger: A Sample-Free Approach to Finding and Fixing Bugs

arXiv

引用

arXiv 2023年

作者： Jiang, Chaoquan Wang, Jinqiang Hu, Rui Sang, Jitao School of Computer and Information Technology Beijing Key Lab of Traffic Data Analysis and Mining Beijing Jiaotong University Beijing China

Vision models with high overall accuracy often exhibit systematic errors on some important subsets of data, posing potential serious safety concerns. Diagnosing such bugs of vision models is gaining increased attention, but traditional diagnostic methods require labor-intensive data collection and attributes annotation. Also, a recent study has demonstrated the cross-modal transferability of the vision-language embedding space and it shows the visual classifiers on top of the space can be diagnosed through natural language. Motivate by these developments, we propose the debugger LaVMD, which enables the vision-language model to proxy the buggy vision model by aligning the embedding spaces without any labeled visual data. Our proposed debugger can discover underperforming subgroups (or slices) in vision models and further improve performances of the subgroups through natural language only. To avoid prior knowledge needed to select candidate visual attribute set, we use a Large Language Model (LLM) to obtain attributes set and probe texts, as the proxy for images to probe visual bugs. Finally, we demonstrate the effectiveness to diagnose underperforming subgroups of buggy vision models using only language on the Waterbirds, CelebA and NICO++. We can identify comprehensible attributes to users and improve buggy model by texts data. Copyright © 2023, The Authors. All rights reserved.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning Based Multi-Task Automated Channel Pruning for DNNs

Deep Reinforcement Learning Based Multi-Task Automated Chann...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Xiaodong Ma Weiwei Fang Beijing Key Lab of Traffic Data Analysis and Mining School of Computer and Information Technology Beijing Jiaotong University Beijing China

Model compression is a key technique that enables deploying Deep Neural Networks (DNNs) on Internet-of-Things (IoT) devices with constrained computing resources and limited power budgets. Channel pruning has become one of the representative compression approaches, but how to determine the compression ratio for different layers of a model still remains as a challenging task. Current automated pruning solutions address this issue by searching for an optimal strategy according to the target compression ratio. Nevertheless, when given a series of tasks with multiple compression ratios and different training datasets, these approaches have to carry out the pruning process repeatedly, which is inefficient and time-consuming. In this paper, we propose a Multi-Task Automated Channel Pruning (MTACP) framework, which can simultaneously generate a number of feasible compressed models satisfying different task demands for a target DNN model. To learn MTACP, the layer-by-layer multi-task channel pruning process is transformed into a Markov Decision Process (MDP), which seeks to solve a series of decision-making problems. Based on this MDP, we propose an actor-critic-based multi-task Reinforcement Learning (RL) algorithm to learn the optimal policy, working based on the IMPortance weighted Actor-Learner Architectures (IMPALA). IMPALA is known as a distributed RL architecture, in which the learner can learn from a set of actors that continuously generate trajectories of experience in their own environments. Extensive experiments on CIFAR10/100 and FLOWER102 datasets for MTACP demonstrate its unique capability for multi-task settings, as well as its superior performance over state-of-the-art solutions.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Character-Level Street View Text Spotting Based on Deep Multisegmentation Network for Smarter Autonomous Driving

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2022年第2期3卷 297-308页

作者： Zhang, Chongsheng Tao, Yuefeng Du, Kai Ding, Weiping Wang, Bin Liu, Ji Wang, Wei Henan Provincial Key Laboratory of Big Data Analysis and Processing Laboratory of the Yellow River Cultural Heritage Henan University Kaifeng475001 China School of Information Science and Technology Nantong University Nantong226019 China School of Electrical Engineering Zhejiang University Hangzhou310058 China Big Data Lab Baidu Inc. Beijing100044 China School of Computer and Information Technology Beijing Jiaotong University Beijing100044 China

Urban scenes are full of street entities with sign boards. Therefore, in autonomous driving, street view text spotting techniques will play a significant role in the precise understanding of surrounding scenes during driving, because texts contained in the images usually provide important clues for accurate image understanding, while it is often ambiguous for existing computer vision algorithms to understand scene images without texts. In this work, we propose a Multi-Segmentation network for character-level scene Text Detection (MSTD). The MSTD introduces a densely connected atrous spatial pyramid pooling module to enlarge the receptive field of the feature extraction layer, so as to localize long as well as large-sized text instances. Moreover, it devises a double segmentation subnetwork to utilize two independent but inherently complementary losses to co-optimize the network and increase the reliability of the confidence scores in predicting the text/nontext areas. With the character instances detected by the MSTD, one can easily perform scene text spotting with classic object recognition networks such as ResNet and DenseNet. We carried out extensive experiments on nine scene text datasets to demonstrate the outstanding performance of the MSTD on character-level and line-level text instance localization and scene text recognition, where the MSTD significantly outperforms the state-of-the-art scene text detection methods and the sequence-to-sequence-learning-based scene text recognizers. © 2020 IEEE.

关键词： Character recognition

来源：评论

学校读者我要写书评

暂无评论

Generating Enlightened Suggestions Based on Mental State Evolution for Emotional Support Conversation 9th

Generating Enlightened Suggestions Based on Mental State Ev...

引用

19th International Conference on Advanced data Mining and Applications, ADMA 2023

作者： Gan, Mengjiao Yu, Jianxing Dong, Xiao Qiu, Shuang Liu, Wei Yin, Jian School of Artificial Intelligence Sun Yat-sen University Zhuhai China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou China Pazhou Lab Guangzhou510330 China Key Laboratory of Sustainable Tourism Smart Assessment Technology Ministry of Culture and Tourism Zhuhai China

ISBN: (纸本)9783031466601

Emotional support conversation aims to provide comfort and suggestions to users and gradually reduce their negative emotions such as anxiety. It is a valuable topic for many applications, including mental health support and customer service chats. However, due to the lack of enough expert knowledge, existing methods fail to provide enlightened suggestions to reverse users’ worries. Additionally, these methods neglect to grasp the mental state evolution of users. To address these problems, we propose a novel method that considers Mental State Evolution to provide Knowledge-grounded Suggestions (MEKS). In detail, we first create a suggestion corpus called MentalQA to grasp the psychological knowledge by resorting to the mental health forum. The relevant passages are selected based on both the context and the original response. Then we leverage graph structure to enrich the context with the inferred user’s mental state evolution. Furthermore, we introduce a gate to combine textual expert knowledge with the mental state evolution graph, so as to facilitate the generation of supportive responses. Experimental results show that this method can provide reasonable solutions to help the users. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Discovery of Emotion Implicit Causes in Products Based on Commonsense Reasoning 9th

Discovery of Emotion Implicit Causes in Products Based on...

引用

19th International Conference on Advanced data Mining and Applications, ADMA 2023

作者： Guo, Qiutong Yu, Jianxing Zhang, Yufeng Jiang, Haowei Liu, Wei Yin, Jian School of Artificial Intelligence Sun Yat-sen University Guangzhou China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou China Pazhou Lab Guangzhou510330 China Key Laboratory of Sustainable Tourism Smart Assessment Technology Ministry of Culture and Tourism Guangzhou China

ISBN: (纸本)9783031466601

This paper focuses on the task of product emotion cause analysis which aims to find essential causes of certain emotions from product reviews. Current works only study the explicit causes which are some spans in the given text. However, some crucial and useful causes may be expressed vaguely. They may not mention but can be inferred from the text semantics. They can capture the deeper reasons to explain some unknown phenomena, which can well support the applications like market research and product optimization. To address this problem, we in this paper propose a new task of Emotion Implicit Cause Discovery (EICD). We develop a novel method that can deduce the implicit causes based on the contexts and commonsense knowledge. Our method first retrieves related knowledge from the large language model to construct reasoning graphs for the emotions and potential causes. We then encode the structural knowledge in the graph and infer the implicit cause by deductive reasoning. To evaluate our method, we construct a large dataset called EICDset, based on Amazon product reviews. Experiments on it demonstrate the effectiveness of our model. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Large dataset

来源：评论

学校读者我要写书评

暂无评论

Community Detection in Temporal Biological Metabolic Networks Based on Semi-NMF Method with Node Similarity Fusion 9th

Community Detection in Temporal Biological Metabolic Networ...

引用

19th International Conference on Advanced data Mining and Applications, ADMA 2023

作者： Zhang, Xuanming Yu, Jianxing Lin, Miaopei Wang, Shiqi Liu, Wei Yin, Jian School of Artificial Intelligence Sun Yat-sen University Zhuhai China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou China Pazhou Lab Guangzhou510330 China Key Laboratory of Sustainable Tourism Smart Assessment Technology Ministry of Culture and Tourism Zhuhai China

ISBN: (纸本)9783031466731

This paper aims to study the topological structure of biological metabolic networks, such as detecting their inherent communities to learn the useful patterns and characteristics. By partitioning a metabolic network into multiple communities and subgraphs, we can reveal their local structure and organization. That helps researchers better understand the structure and function of metabolic networks, identify metabolic pathways and functional modules, and discover mechanisms and patterns of metabolic regulation. However, community detection remains a challenging problem due to the dynamic nature of metabolic network structure and data sparsity. To address this problem, we propose a new temporal community detection method for biological metabolic networks based on a semi-NMF framework with node similarity fusion, called SNF-MNet. This method grasps the dynamic nature of metabolic networks by introducing temporal smoothness to estimate network evolution. Furthermore, SNF-MNet adopts a node similarity fusion method to comprehensively consider the relations between nodes in the network, effectively solving the limitations and data sparsity issues of existing methods. SNF-MNet can effectively reduce the impact of noise and improve discriminability in small communities, providing more accurate and reliable results. Experiments on multiple synthetic and real-world datasets demonstrate the effectiveness of this model in community detection and temporal evolution tracking, with an increase of NMI 1%–3.2%. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Metabolism

来源：评论

学校读者我要写书评

暂无评论

Neural processes with stability 23

Neural processes with stability

引用

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Huafeng Liu Liping Jing Jian Yu Beijing Key Lab of Traffic Data Analysis and Mining Beijing Jiaotong University and The School of Computer and Information Technology Beijing Jiaotong University

Unlike traditional statistical models depending on hand-specified priors, neural processes (NPs) have recently emerged as a class of powerful neural statistical models that combine the strengths of neural networks and stochastic processes. NPs can define a flexible class of stochastic processes well suited for highly non-trivial functions by encoding contextual knowledge into the function space. However, noisy context points introduce challenges to the algorithmic stability that small changes in training data may significantly change the models and yield lower generalization performance. In this paper, we provide theoretical guidelines for deriving stable solutions with high generalization by introducing the notion of algorithmic stability into NPs, which can be flexible to work with various NPs and achieves less biased approximation with theoretical guarantees. To illustrate the superiority of the proposed model, we perform experiments on both synthetic and real-world data, and the results demonstrate that our approach not only helps to achieve more accurate performance but also improves model robustness.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Cross-Domain Rumor Detection with Contrastive Learning and Cross-Attention

arXiv

引用

arXiv 2023年

作者： Ran, Hongyan Jia, Caiyan School of Computer and Information Technology Beijing Key Lab of Traffic Data Analysis and Mining Beijing Jiaotong University Beijing100044 China

Massive rumors usually appear along with breaking news or trending topics, seriously hindering the truth. Existing rumor detection methods are mostly focused on the same domain, thus have poor performance in cross-domain scenarios due to domain shift. In this work, we propose an end-to-end instance-wise and prototype-wise contrastive learning model with cross-attention mechanism for cross-domain rumor detection. The model not only performs cross-domain feature alignment, but also enforces target samples to align with the corresponding prototypes of a given source domain. Since target labels in a target domain are unavailable, we use a clustering-based approach with carefully initialized centers by a batch of source domain samples to produce pseudo labels. Moreover, we use a cross-attention mechanism on a pair of source data and target data with the same labels to learn domain-invariant representations. Because the samples in a domain pair tend to express similar semantic patterns especially on the people’s attitudes (e.g., supporting or denying) towards the same category of rumors, the discrepancy between a pair of source domain and target domain will be decreased. We conduct experiments on four groups of cross-domain datasets and show that our proposed model achieves state-of-the-art performance. © 2023, CC0.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

CoCGAN: Contrastive Learning for Adversarial Category Text Generation 29

CoCGAN: Contrastive Learning for Adversarial Category Text G...

引用

29th International Conference on Computational Linguistics, COLING 2022

作者： Sheng, Xin Xu, Linli Xu, Yinlong Bao, Changcun Chen, Huang Ren, Bo Anhui Province Key Laboratory of Big Data Analysis and Application School of Computer Science and Technology University of Science and Technology of China China School of Computer Science and Technology University of Science and Technology of China China State Key Laboratory of Cognitive Intelligence China Tencent Youtu Lab China

The task of generating texts of different categories has attracted more and more attention in the area of natural language generation recently. Meanwhile, generative adversarial net (GAN) has demonstrated its effectiveness on text generation, and is further applied to category text generation in later works. Different from existing methods, which mainly consider the pairwise relations between the text embedding and the corresponding fixed one-hot class label (data-to-class relations), this paper proposes a novel Contrastive Category Generative Adversarial Net (CoCGAN) to incorporate contrastive learning into adversarial category text generation, considering more flexible data-to-class relations as well as relations between the multiple text embeddings in the same batch (data-to-data relations). The discriminator of CoCGAN discriminates the authenticity of given samples and optimizes a contrastive learning objective to capture both more flexible data-to-class relations and data-to-data relations among training samples. Accordingly, the generator tries to produce more realistic samples which can confuse the discriminator. Experimental results on both synthetic and real category text generation datasets demonstrate that CoCGAN can achieve significant improvements over the baseline category text generation models. © 2022 Proceedings - International Conference on Computational Linguistics, COLING. All rights reserved.

关键词： Embeddings

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：