检索结果-内蒙古大学图书馆

Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, ACL-IJCNLP 2021

作者： Xu, Zenan Guo, Daya Tang, Duyu Su, Qinliang Shou, Linjun Gong, Ming Zhong, Wanjun Quan, Xiaojun Jiang, Daxin Duan, Nan School of Computer Science and Engineering Sun Yat-Sen University Guangzhou China Microsoft Research Asia Beijing China Microsoft Search Technology Center Asia Beijing China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou China Key Lab. of Machine Intelligence and Advanced Computing Ministry of Education China

ISBN: (纸本)9781954085527

We study the problem of leveraging the syntactic structure of text to enhance pre-trained models such as BERT and RoBERTa. Existing methods utilize syntax of text either in the pre-training stage or in the fine-tuning stage, so that they suffer from discrepancy between the two stages. Such a problem would lead to the necessity of having human-annotated syntactic information, which limits the application of existing methods to broader scenarios. To address this, we present a model that utilizes the syntax of text in both pre-training and fine-tuning stages. Our model is based on Transformer with a syntax-aware attention layer that considers the dependency tree of the text. We further introduce a new pre-training task of predicting the syntactic distance among tokens in the dependency tree. We evaluate the model on three downstream tasks, including relation classification, entity typing, and question answering. Results show that our model achieves state-of-the-art performance on six public benchmark datasets. We have two major findings. First, we demonstrate that infusing automatically produced syntax of text improves pre-trained models. Second, global syntactic distances among tokens bring larger performance gains compared to local head relations between contiguous tokens. © 2021 Association for Computational Linguistics

关键词： Syntactics

来源：评论

学校读者我要写书评

暂无评论

Incremental Learning Algorithm Based on Graph Regularized Non-negative Matrix Factorization with Sparseness Constraints 4

Incremental Learning Algorithm Based on Graph Regularized No...

引用

4th International Conference on Artificial Intelligence and Big data, ICAIBD 2021

作者： Wang, Jintao Zhang, Meng Hu, Xusheng Ni, Tianwei Key Lab. of Unmanned Aer. Vehicle Devmt. and Data Application of Anhui Higher Education Institutes Maanshan Wireless Sensor Network and Intelligent Perception Engineering Technology Research Center Wanjiang University of Technology Maanshan China Wanjiang University of Technology Maanshan China

ISBN: (纸本)9780738131702

Focused on the issues that the sparseness of the data obtained after factorization is reduced and with the increasing of training samples, the computing scale increases rapidly, an incremental learning algorithm based on graph regularized non-negative matrix factorization with sparseness constraints was proposed. It not only considers the geometric structure in the data representation, but also introduces sparseness constraint to coefficient matrix and combines them with incremental learning. Using the results of previous factorization involved in iterative computation with sparseness constraints and graph regularized, the cost of the computation is reduced and the sparseness of data after factorization is highly improved. Experiments on both ORL and PIE face recognition databases demonstrate the effectiveness of the proposed method. © 2021 IEEE.

关键词： Non-negative matrix factorization

来源：评论

学校读者我要写书评

暂无评论

Not All Diffusion Model Activations Have Been Evaluated as Discriminative Features 38

Not All Diffusion Model Activations Have Been Evaluated as D...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Meng, Benyuan Xu, Qianqian Wang, Zitai Cao, Xiaochun Huang, Qingming Institute of Information Engineering CAS China School of Cyber Security University of Chinese Academy of Sciences China Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS China Peng Cheng Laboratory China School of Cyber Science and Tech. Shenzhen Campus of Sun Yat-sen University China School of Computer Science and Tech. University of Chinese Academy of Sciences China Key Laboratory of Big Data Mining and Knowledge Management CAS China

Diffusion models are initially designed for image generation. Recent research shows that the internal signals within their backbones, named activations, can also serve as dense features for various discriminative tasks such as semantic segmentation. Given numerous activations, selecting a small yet effective subset poses a fundamental problem. To this end, the early study of this field performs a large-scale quantitative comparison of the discriminative ability of the activations. However, we find that many potential activations have not been evaluated, such as the queries and keys used to compute attention scores. Moreover, recent advancements in diffusion architectures bring many new activations, such as those within embedded ViT modules. Both combined, activation selection remains unresolved but overlooked. To tackle this issue, this paper takes a further step with a much broader range of activations evaluated. Considering the significant increase in activations, a full-scale quantitative comparison is no longer operational. Instead, we seek to understand the properties of these activations, such that the activations that are clearly inferior can be filtered out in advance via simple qualitative evaluation. After careful analysis, we discover three properties universal among diffusion models, enabling this study to go beyond specific models. On top of this, we present effective feature selection solutions for several popular diffusion models. Finally, the experiments across multiple discriminative tasks validate the superiority of our method over the SOTA competitors. Our code is availab.e at this url. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Measurement of absorption spectroscopy enabled by a polarization-multiplexed dual-comb laser

Measurement of absorption spectroscopy enabled by a polariza...

引用

2023 IEEE International Conference on Imaging Systems and Techniques, IST 2023

作者： Zhang, Chenghong Wang, Gang Sun, Jingxuan Fu, Bo Xu, Lijun Beihang University School of Instrumentation and Optoelectronic Engineering Beijing China Beihang University Key Lab. of Big Data-Based Prec. Med. Min. of Indust. and Info. Technol. Sch. of Eng. Medicine Beijing China

ISBN: (纸本)9798350330830

Absorption spectroscopy has been widely used in non-intrusive chemical analysis. Dual-comb spectroscopy is emerging as an effective tool for the measurement of absorption spectroscopy with both high resolution and wide bandwidth. Herein, we proposed a simple measurement of the absorption spectrum based on a polarization-multiplexed dual-comb laser. The free-running dual combs generated from a single cavity were highly coherent. In addition, the two combs possess overlapped spectra. Therefore, the dual-comb laser was utilized to perform dual-comb spectroscopy directly without a servo-locking system. The signal-to-noise ratio of interferograms in the time domain was effectively improved by the coherent average. The linear relationship between the signal-to-noise ratio and the square root of average times indicated the dual-comb laser was highly coherent. Taking advantage of the stable dual-comb laser, the extracted weak absorption features of hydrogen cyanide within the wavelength range of 1560 to 1566 nm were in line with the HITRAN database. To the best of our knowledge, it is the first time to realize the measurement of absorption spectrum at 1.5-μm with dual combs under such low repetition rates. Such kind of dual-comb laser provides an effective approach for the realization of low-cost and high-resolution absorption spectroscopy. The simple and high-resolution dual-comb spectrometer could be further applied in quantitative measurements based on absorption spectroscopy, such as measurements of temperature and concentration. © 2023 IEEE.

关键词： Absorption spectroscopy

来源：评论

学校读者我要写书评

暂无评论

Pre-training for ad-hoc retrieval: Hyperlink is also you need

arXiv

引用

arXiv 2021年

作者： Ma, Zhengyi Dou, Zhicheng Xu, Wei Zhang, Xinyu Jiang, Hao Cao, Zhao Wen, Ji-Rong Gaoling School of Artificial Intelligence Renmin University of China Beijing China Distributed and Parallel Software Lab Huawei Beijing Key Laboratory of Big Data Management and Analysis Methods Beijing China Key Laboratory of Data Engineering and Knowledge Engineering MOE Beijing China

Designing pre-training objectives that more closely resemble the downstream tasks for pre-trained language models can lead to better performance at the fine-tuning stage, especially in the ad-hoc retrieval area. Existing pre-training approaches tailored for IR tried to incorporate weak supervised signals, such as query-likelihood based sampling, to construct pseudo query-document pairs from the raw textual corpus. However, these signals rely heavily on the sampling method. For example, the query likelihood model may lead to much noise in the constructed pre-training data. In this paper, we propose to leverage the large-scale hyperlinks and anchor texts to pre-train the language model for ad-hoc retrieval. Since the anchor texts are created by webmasters and can usually summarize the target document, it can help to build more accurate and reliable pre-training samples than a specific algorithm. Considering different views of the downstream ad-hoc retrieval, we devise four pre-training tasks based on the hyperlinks. We then pre-train the Transformer model to predict the pair-wise preference, jointly with the Masked Language Model objective. Experimental results on two large-scale ad-hoc retrieval datasets show the significant improvement of our model compared with the existing methods. Copyright © 2021, The Authors. All rights reserved.

关键词： Hypertext systems

来源：评论

学校读者我要写书评

暂无评论

Feature re-learning with data augmentation for video relevance prediction

arXiv

引用

arXiv 2020年

作者： Dong, Jianfeng Wang, Xun Zhang, Leimin Xu, Chaoxi Yang, Gang Li, Xirong College of Computer and Information Engineering Zhejiang Gongshang University Hangzhou310035 China Key Lab of Data Engineering and Knowledge Engineering Renmin University of China AI & Media Computing Lab School of Information Renmin University of China Beijing100872 China

Predicting the relevance between two given videos with respect to their visual content is a key component for content-based video recommendation and retrieval. Thanks to the increasing availab.lity of pre-trained image and video convolutional neural network models, deep visual features are widely used for video content representation. However, as how two videos are relevant is task-dependent, such off-the-shelf features are not always optimal for all tasks. Moreover, due to varied concerns including copyright, privacy and security, one might have access to only pre-computed video features rather than original videos. We propose in this paper feature re-learning for improving video relevance prediction, with no need of revisiting the original video content. In particular, re-learning is realized by projecting a given deep feature into a new space by an affine transformation. We optimize the re-learning process by a novel negative-enhanced triplet ranking loss. In order to generate more training data, we propose a new data augmentation strategy which works directly on frame-level and video-level features. Extensive experiments in the context of the Hulu Content-based Video Relevance Prediction Challenge 2018 justify the effectiveness of the proposed method and its state-of-the-art performance for content-based video relevance prediction. Copyright © 2020, The Authors. All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Image manipulation detection by multi-view multi-scale supervision

arXiv

引用

arXiv 2021年

作者： Chen, Xinru Dong, Chengbo Ji, Jiaqi Cao, Juan Li, Xirong MoE Key Lab of Data Engineering and Knowledge Engineering Renmin University of China AIMC Lab School of Information Renmin University of China Institute of Computing Technology Chinese Academy of Sciences State Key Laboratory of Media Convergence Production Technology and Systems

The key challenge of image manipulation detection is how to learn generalizable features that are sensitive to manipulations in novel data, whilst specific to prevent false alarms on authentic images. Current research emphasizes the sensitivity, with the specificity overlooked. In this paper we address both aspects by multi-view feature learning and multi-scale supervision. By exploiting noise distribution and boundary artifact surrounding tampered regions, the former aims to learn semantic-agnostic and thus more generalizable features. The latter allows us to learn from authentic images which are nontrivial to be taken into account by current semantic segmentation network based methods. Our thoughts are realized by a new network which we term MVSS-Net. Extensive experiments on five benchmark sets justify the viability of MVSS-Net for both pixel-level and image-level manipulation detection. Copyright © 2021, The Authors. All rights reserved.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Image Manipulation Detection by Multi-View Multi-Scale Supervision

Image Manipulation Detection by Multi-View Multi-Scale Super...

引用

International Conference on Computer Vision (ICCV)

作者： Xinru Chen Chengbo Dong Jiaqi Ji Juan Cao Xirong Li MoE Key Lab of Data Engineering and Knowledge Engineering Renmin University of China AIMC Lab School of Information Renmin University of China Institute of Computing Technology Chinese Academy of Sciences State Key Laboratory of Media Convergence Production Technology and Systems

ISBN: (纸本)9781665428132

关键词： Representation learning Image segmentation Computer vision Sensitivity Costs Image edge detection Semantics

来源：评论

学校读者我要写书评

暂无评论

Industrial Region Planning and Urban Transportation Planning Based on Industry-City Integration 6

Industrial Region Planning and Urban Transportation Planning...

引用

6th International Conference on Transportation Information and Safety, ICTIS 2021

作者： Zheng, Shuai Liu, Yugang Zhang, Jia Wan, Qing Zhang, Heyang Ye, Jinsong Southwest Jiaotong University School of Transportation and Logistics Southwest Jiaotong University National United Engineering Laboratory of Integrated Intelligent TransPortation Chengdu China Key Lab. of Transport Industry of Big Data Application Technologies for Comprehensive Transport China Academy of Transportation Sciences Beijing100029 China

ISBN: (纸本)9781665497138

With urban expansion and economic development, traditional industrial parks with single function cannot adapt to the pace of urban development. As a new type of industrial park, the industry-city integration has gradually become the development direction. There is no tailor-made quantitative planning scheme at this stage. Aiming at filling the gap, this research does the following work to provide quantitative guidance strategy for industrial park planning. This paper first analyzes the Transit-oriented development (TOD) model requirements of new industrial parks, and makes a detailed analysis of the interaction between land use and transportation. Secondly, based on the relationship between land use and transportation, a combined feedback model of the land planning model and the public transportation utility allocation model is established. The process of modeling is to plan the smallest land unit according to the principle of land use function combination and land use type to meet the needs of residents. The other is to plan public transportation with optimal road load according to the principle of public transportation guiding travel and maximizing travel efficiency. Notedly, this paper uses the TOPSIS method to normalize the planning score through the feedback relationship between land use planning and public transportation planning. Based the analysis, the genetic algorithm is used to optimize the planning score and obtain the best plan which provides quantitative guidance strategies for the industrial park planning. Finally, this paper selects the 'Blank Land' of Suzhou Industrial Parks for case analysis, and the best standardized score after planning is about 87 points. In order to further analyze the planning effect and the relationship between the planned area and the rest of the land, ArcGIS is used to carry out demand analysis and land use radiation range analysis of the planning scheme. The results show that the travel demand after planning matches with t

关键词： Land use

来源：评论

学校读者我要写书评

暂无评论

IKGN: Intention-aware knowledge Graph Network for POI Recommendation

IKGN: Intention-aware Knowledge Graph Network for POI Recomm...

引用

IEEE International Conference on data Mining (ICDM)

作者： Xiaoyu Zhu Chenyang Bu Bingbing Dong Shengwei Ji Yi He Xindong Wu Key Laboratory of Knowledge Engineering with Big Data (the Ministry of Education of China) Hefei University of Technology School of Computer Science and Information Engineering Hefei University of Technology China School of Artificial Intelligence and Big Data Hefei University China Department of Computer Science Old Dominion University USA Research Center for Knowledge Engineering Zhejiang Lab China

Point-of-Interest (POI) recommendation, pivotal for guiding users to their next interested locale, grapples with the persistent challenge of data sparsity. Whereas knowledge graphs (KGs) have emerged as a favored tool to mitigate the issue, existing KG-based methods tend to overlook two crucial elements: the intention steering users’ location choices and the high-order topological structure within the KG. In this paper, we craft an Intention-aware knowledge Graph (IKG) that harmonizes users’ visit histories, movement trajectories, and location categories to model user intentions. Building upon IKG, our novel Intention-aware knowledge Graph Network (IKGN) delves deeper into the POI recommendation by weighing and propagating node embeddings through an attention mechanism, capturing the unique locational intent of each user. A sequential model like GRU is then employed to ensure a comprehensive representation of users’ short- and long-term location preferences. An empirical study on two real-world datasets validates the effectiveness of our proposed IKGN, with it markedly outshining seven benchmark rival models in both Recall and NDCG metrics. The code of IKGN is availab.e at https://***/Jungle123456/IKGN.

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：