检索结果-内蒙古大学图书馆

28th Text REtrieval Conference, TREC 2019

作者： Guangsheng, Kuang Kun, Zhang Jiabao, Zhang Xin, Zheng University of Chinese Academy of Sciences Beijing China CAS Key Lab of Network Data Science and Technology Institute of Computing Technology China

Social medial become our public ways to share our information in our lives. Crisis management via social medial is becoming indispensable for its tremendous information. While deep learning shows surprising outcome in many tasks. So in this paper, we cope this learning task with neural network in the view of classification problem. © 2019 28th Text REtrieval Conference, TREC 2019 - Proceedings. All Rights Reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

ICTNET at TREC 2019 News Track 28

ICTNET at TREC 2019 News Track

引用

28th Text REtrieval Conference, TREC 2019

作者： Ding, Yuyang Lian, Xiaoying Zhou, Houquan Liu, Zhaoge Ding, Hanxing Hou, Zhongni University of Chinese Academy of Sciences Beijing China CAS Key Lab of Network Data Science and Technology Institute of Computing Technology China

This paper describes our work in the background linking task and entity ranking task in TREC 2018 News Track. We explore four methods in background linking task and two methods in entity ranking task. All of our methods largely rely on off-the-shell open-source components(e.g., Solr for indexing the documents), and follow the basic thoughts-BM25 and relevance feedback. These methods differ in how they analyze the given input to obtain a query and to what extent the returned results are re-ranked taking meta data of the document(e.g., publish dates) into account. © 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

ICTNET at TREC 2019 Complex Answer Retrieval Track 28

ICTNET at TREC 2019 Complex Answer Retrieval Track

引用

28th Text REtrieval Conference, TREC 2019

作者： Ren, Hongfei Xiong, Ruibin Zeng, Yutao Chen, Jiangui Cai, Yinqiong Jiang, Haoquan University of Chinese Academy of Sciences Beijing China CAS Key Lab of Network Data Science and Technology Institute of Computing Technology China

We participate in the Complex Answer Retrieval(CAR) track at TREC 2019. We applied several useful models in this work. In the rough ranking, we applied doc2query model to predict queries and retrieve using BM25. In the re-ranking, we submitted 5 different runs which use 5 different models, include BM25, DRMMTKS, Bert-DRMMTKS, Bert-ConvKNRM and Bert-ConvKNRM-50, to try to get the best result. © 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

Match-SRNN: Modeling the recursive matching structure with spatial RNN 25

Match-SRNN: Modeling the recursive matching structure with s...

引用

25th International Joint Conference on Artificial Intelligence, IJCAI 2016

作者： Wan, Shengxian Lan, Yanyan Xu, Jun Guo, Jiafeng Pang, Liang Xueqi, Cheng CAS Key Lab of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China

Semantic matching, which aims to determine the matching degree between two texts, is a fundamental problem for many NLP applications. Recently, deep learning approach has been applied to this problem and significant improvements have been achieved. In this paper, we propose to view the generation of the global interaction between two texts as a recursive process: i.e. the interaction of two texts at each position is a composition of the interactions between their prefixes as well as the word level interaction at the current position. Based on this idea, we propose a novel deep architecture, namely Match-SRNN, to model the recursive matching structure. Firstly, a tensor is constructed to capture the word level interactions. Then a spatial RNN is applied to integrate the local interactions recursively, with importance determined by four types of gates. Finally, the matching score is calculated based on the global interaction. We show that, after degenerated to the exact matching scenario, Match-SRNN can approximate the dynamic programming process of longest common subsequence. Thus, there exists a clear interpretation for Match-SRNN. Our experiments on two semantic matching tasks showed the effectiveness of Match-SRNN, and its ability of visualizing the learned matching structure.

关键词： Dynamic programming

来源：评论

学校读者我要写书评

暂无评论

ICTNET at Trec 2019 Decision Track 28

ICTNET at Trec 2019 Decision Track

引用

28th Text REtrieval Conference, TREC 2019

作者： Cui, Wanqing Jiang, Yan Tao, Shuchang Guo, Hanzhang CAS Key Lab of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China

In this paper we report on our participation in the Trec 2019 Decision Track[1] which aims to provide a venue for research on retrieval methods that promote better decision making with search engines and develop new online and offline evaluation methods to predict the decision making quality induced by search results. We convert this task into a standard information retrieval task and use traditional IR model. Finally we give a summary for the solution of our work. © 2019 28th Text REtrieval Conference, TREC 2019 - Proceedings. All Rights Reserved.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Predict anchor links across social networks via an embedding approach 25

Predict anchor links across social networks via an embedding...

引用

25th International Joint Conference on Artificial Intelligence, IJCAI 2016

作者： Man, Tong Shen, Huawei Liu, Shenghua Jin, Xiaolong Cheng, Xueqi CAS Key Lab of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China

Predicting anchor links across social networks has important implications to an array of applications, including cross-network information diffusion and cross-domain recommendation. One challenging problem is: whether and to what extent we can address the anchor link prediction problem, if only structural information of networks is available. Most existing methods, unsupervised or supervised, directly work on networks themselves rather than on their intrinsic structural regularities, and thus their effectiveness is sensitive to the high dimension and sparsity of networks. To offer a robust method, we propose a novel supervised model, called PALE, which employs network embedding with awareness of observed anchor links as supervised information to capture the major and specific structural regularities and further learns a stable cross-network mapping for predicting anchor links. Through extensive experiments on two realistic datasets, we demonstrate that PALE significantly outperforms the state-of-the-art methods.

关键词： network embeddings

来源：评论

学校读者我要写书评

暂无评论

Modeling retail transaction data for personalized shopping recommendation 14

Modeling retail transaction data for personalized shopping r...

引用

23rd ACM International Conference on Information and Knowledge Management, CIKM 2014

作者： Wang, Pengfei Guo, Jiangfeng Lan, Yanyan Cheng, Xueqi Key Lab. of Network Data Science and Technology ICT Beijing China

ISBN: (纸本)9781450325981

Retail transaction data conveys rich preference information on brands and goods from customers. How to mine the transaction data to provide personalized recommendation to customers becomes a critical task for retailers. Previous recommendation methods either focus on the user-product matrix and ignore the transactions, or only use the partial information of transactions, leading to inferior performance in recommendation. Inspired by association rule mining, we introduce association pattern as a basic unit to capture the correlation between products from both intra- and intertransactions. A Probabilistic model over the Association Patterns (PAP for short) is then employed to learn the potential shopping interests and also to provide personalized recommendations. Experimental results on two real world retail data sets show that our proposed method can outperform the state-of-the-art recommendation methods. Copyright 2014 ACM.

关键词： Sales

来源：评论

学校读者我要写书评

暂无评论

Lineament extraction and structural mapping using Landsat-9 OLI and Sentinel-1 SAR data in the Proterozoic North Singhbhum Mobile Belt, Eastern India

引用

Geosystems and Geoenvironment 2025年第3期4卷

作者： Choudhury, Nandini Mitra, Atin Kumar Nath, Biswajit Lindsay, Mark D Structural Geology Laboratory Department of Earth Sciences Indian Institute of Engineering Science and Technology West Bengal Shibpur 711103 India Lab of Geoinformatics and Earth Observation Research (LGEOR) Department of Geography and Environmental Studies Faculty of Biological Sciences University of Chittagong Chittagong 4331 Bangladesh CAS-PIFI Visiting Scientist State Key Laboratory of Remote Sensing Science Aerospace Information Research Institute (AIR) Chinese Academy of Sciences (CAS) Olympic Science and Technology Park 20 Datun Road Chaoyang District Beijing 100101 China CSIRO Mineral Resources Kensington 6151 WA Australia School of Earth Sciences The University of Western Australia Crawley 6009 WA Australia ARC Industrial Transformation Training Centre in Data Analytics for Resources and Environment (DARE) Perth and Sydney Australia

The present study explores the application of Landsat-9 OLI and Sentinel-1 SAR data for effective lineament extraction and structural mapping in the Proterozoic North Singhbhum Mobile Belt, Eastern India, an area characterized by complex geological and significant tectonic history. The study employs a combination of manual and automated lineament extraction techniques, with principal component analysis (PCA) applied to Landsat 9 OLI imagery to enhance the visibility of underlying geological structures. The analysis revealed that PC1 captured the highest accuracy for lineament extraction. Sentinel-1 SAR data, acquired in Interferometric Wide (IW) swath mode with dual polarization (VV and VH), was processed using Google Earth Engine, allowing for detailed analysis of surface features. The VH polarization was particularly effective in detecting fine-scale linear features due to its sensitivity to surface roughness and vegetation penetration. Field data collection was integral to the research, allowing for the validation of remote sensing results and the construction of a detailed regional structural map. Stereographic projections were utilized to analyse and visualize structural orientations, including schistosity, lineations, shear foliations and fold axes, providing insights into the area's tectonic evolution. The comparative analysis of lineament characteristics from Landsat-9 OLI and Sentinel-1 SAR datasets indicated that while Sentinel-1 detected a greater number of shorter lineaments, Landsat-9 provided longer lineaments with distinct orientations. This study underscores the efficacy of integrating remote sensing data with field observations and advanced analytical tools, contributing to a deeper understanding of the geological framework. © 2025 The Authors

关键词： Landsat-9 OLI Lineament extraction Sentinel-1 SAR Singhbhum shear zone Stereonet Structural mapping

来源：评论

学校读者我要写书评

暂无评论

AdaptFRCNet: Semi-supervised adaptation of pre-trained model with frequency and region consistency for medical image segmentation

引用

Medical Image Analysis 2025年 103卷 103626页

作者： Along He Yanlin Wu Zhihong Wang Tao Li Huazhu Fu College of Computer Science Tianjin Key Laboratory of Network and Data Security Technology Nankai University Tianjin 300350 China Haihe Lab of ITAI Tianjin 300459 China Institute of High Performance Computing (IHPC) Agency for Science Technology and Research (A*STAR) 138632 Singapore

Recently, large pre-trained models (LPM) have achieved great success, which provides rich feature representation for downstream tasks. Pre-training and then fine-tuning is an effective way to utilize LPM. However, the application of LPM in the medical domain is hindered by the presence of a large number of parameters and a limited amount of labeled data. In clinical practice, there exists a substantial amount of unlabeled data that remains underutilized. Semi-supervised learning emerges as a promising approach to harnessing these unlabeled data effectively. In this paper, we propose semi-supervised adaptation of pre-trained model with frequency and region consistency (AdaptFRCNet) for medical image segmentation. Specifically, the pre-trained model is frozen and the proposed lightweight attention-based adapters (Att_Adapter) are inserted into the frozen backbone for parameter-efficient fine-tuning (PEFT). We propose two consistency regularization strategies for semi-supervised learning: frequency domain consistency (FDC) and multi-granularity region similarity consistency (MRSC). FDC aids in learning features within the frequency domain, and MRSC aims to achieve multiple region-level feature consistencies, capturing local context information effectively. By leveraging the proposed Att_Adapter along with FDC and MRSC, we can effectively and efficiently harness the powerful feature representation capability of the LPM. We conduct extensive experiments on three medical image segmentation datasets, demonstrating significant performance improvements over other state-of-the-art methods. The code is available at https://***/NKUhealong/AdaptFRCNet .

关键词： Consistency regularization Medical image segmentation Parameter-efficient fine-tuning Semi-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Visual Named Entity Linking: A New dataset and A Baseline

Visual Named Entity Linking: A New Dataset and A Baseline

引用

2022 Findings of the Association for Computational Linguistics: EMNLP 2022

作者： Sun, Wenxiang Fan, Yixing Guo, Jiafeng Zhang, Ruqing 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

Visual Entity Linking (VEL) is a task to link regions of images with their corresponding entities in Knowledge Bases (KBs), which is beneficial for many computer vision tasks such as image retrieval, image caption, and visual question answering. While existing tasks in VEL either rely on textual data to complement a multi-modal linking or only link objects with general entities, which fails to perform named entity linking on large amounts of image data. In this paper, we consider a purely Visual-based Named Entity Linking (VNEL) task, where the input only consists of an image. The task is to identify objects of interest (i.e., visual entity mentions) in images and link them to corresponding named entities in KBs. Since each entity often contains rich visual and textual information in KBs, we thus propose three different sub-tasks, i.e., visual to visual entity linking (V2VEL), visual to textual entity linking (V2TEL), and visual to visual-textual entity linking (V2VTEL). In addition, we present a high-quality human-annotated visual person linking dataset, named WIKIPerson. Based on WIKIPerson, we establish a series of baseline algorithms for the solution of each sub-task, and conduct experiments to verify the quality of the proposed datasets and the effectiveness of baseline methods. We envision this work to be helpful for soliciting more works regarding VNEL in the future. The codes and datasets are publicly available at https://***/ict-bigdatalab/VNEL. © 2022 Association for Computational Linguistics.

关键词： Image retrieval

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：