检索结果-内蒙古大学图书馆

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

Co-training Based on Semi-Supervised Ensemble Classification Approach for Multi-label data Stream

Co-training Based on Semi-Supervised Ensemble Classification...

引用

IEEE International Conference on Big knowledge (ICBK)

作者： Zhe Chu Peipei Li Xuegang Hu Key Laboratory of Knowledge Engineering with Big Data (Hefei University of Technology) Ministry of Education AnHui China School of Computer Science and Information Engineering Hefei University of Technology AnHui China

A large amount of data streams in the form of texts and images has been emerging in many real-world applications. These data streams often present the characteristics such as multi-labels, label missing and new class emerging, which makes the existing data stream classification algorithm face the challenges in precision space and time performance. This is because, on the one hand, it is known that data stream classification algorithms are mostly trained on all labeled single-class data, while there are a large amount of unlabeled data and few labeled data due to it is difficult to obtain labels in the real world. On the other hand, many of existing multi-label data stream classification algorithms mostly focused on the classification with all labeled data and without emerging new classes, and there are few semi-supervised methods. Therefore, this paper proposes a semi-supervised ensemble classification algorithm for multi-label data streams based on co-training. Firstly, the algorithm uses the sliding window mechanism to partition the data stream into data chunks. On the former w data chucks, the multi-label semi-supervised classification algorithm COINS based on co-training is used to training a base classifier on each chunk, and then an ensemble model with w COINS classifiers is generated ensemble model to adapt to the environment of data stream with a large number of unlabeled data. Meanwhile, a new class emerging detection mechanism is introduced, and the w+1 data chunk is predicted by the ensemble model to detect whether there is a new class emerging. When a new label is detected, the classifier is retrained on the current data chunk, and the ensemble model is updated. Finally, experimental results on five real data sets show that: as compared with the classical algorithms, the proposed approach can improve the classification accuracy of multi-label data streams with a large number of missing labels and new labels emerging.

关键词： data models Training Streaming media Adaptation models Partitioning algorithms Correlation knowledge engineering

来源：评论

学校读者我要写书评

暂无评论

Classification of Table Cells Based on LLM Prompts

Classification of Table Cells Based on LLM Prompts

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Mengjie Liu Chenyang Bu Shengxing Bai Bingbing Dong Xindong Wu Key Laboratory of Knowledge Engineering with Big Data (the Ministry of Education of China) Hefei University of Technology China School of Computer Science and Information Engineering Hefei University of Technology Hefei China

ISBN: (数字)9781665410205

ISBN: (纸本)9781665410212

Tables, as an important means of data storage, are widely used in spreadsheets, web tables, and PDFs. By integrating information from table data with knowledge re-trieved from an external knowledge base, and examining the correspondences between cell values in the table and instances in the knowledge base, we can extract knowledge from the table to augment and enrich the knowledge base. To achieve this goal, we first need to classify table cells based on their functions in the layout. Due to the diverse structures arising from the arrangements of rows and columns, as well as the complexity of content resulting from concise data storage, current automation techniques heavily rely on stylistic features of table cells, such as font or color. Moreover, these methods are rarely experimented with or validated on tables without style features. Recent literature indicates that large language models (LLMs) demonstrate an ability to understand the structure and content of tables in tasks such as table judgment reasoning. Even without extensive feature inputs or pre-training, LLMs still show comparable results to machine learning and deep learning in these tasks. Therefore, this paper attempts to apply LLMs to table cell classification without using other stylistic features. We have designed a 4-component prompt paradigm (Classification Definition, Instruction, Table, Com-pletion), representing respectively the classification definition, task instructions, table data, and result output. We conduct experiments on three datasets CIUS, SAUS, and DEEX for table cell classification with one-shot learning. Our experimental results show that with the assistance of LLMs, better results can be achieved without utilizing stylistic features.

关键词： Deep learning Image color analysis Large language models knowledge based systems Layout Memory One shot learning Benchmark testing Probability density function data mining

来源：评论

学校读者我要写书评

暂无评论

One-bit supervision for image classification

arXiv

引用

arXiv 2020年

作者： Hu, Hengtong Xie, Lingxi Du, Zewei Hong, Richang Tian, Qi Key Laboratory of Knowledge Engineering with Big Data Hefei University of Technology China School of Computer Science and Information Engineering Hefei University of Technology China Huawei Inc. China

This paper presents one-bit supervision, a novel setting of learning from incomplete annotations, in the scenario of image classification. Instead of training a model upon the accurate label of each sample, our setting requires the model to query with a predicted label of each sample and learn from the answer whether the guess is correct. This provides one bit (yes or no) of information, and more importantly, annotating each sample becomes much easier than finding the accurate label from many candidate classes. There are two keys to training a model upon one-bit supervision: improving the guess accuracy and making use of incorrect guesses. For these purposes, we propose a multi-stage training paradigm which incorporates negative label suppression into an off-the-shelf semi-supervised learning algorithm. In three popular image classification benchmarks, our approach claims higher efficiency in utilizing the limited amount of annotations. Copyright © 2020, The Authors. All rights reserved.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

引用

Journal of Convergence Information Technology 2012年第16期7卷 87-96页

作者： Minjuan, Zhong School of Information Technology Jiangxi University of Finance and Economics Nanchang 330013 China Jiangxi Key Laboratory of Data and Knowledge Engineering Jiangxi University of Finance and Economics Nanchang 330013 China

With the increasing of XML data over the Internet, managing and analyzing huge amount of XML documents has played an important role for information management. Clustering as an intelligent technique has been utilized as an excellent way of grouping the documents by their content or structure. However, the key problem is how to measure similarity between XML documents. In this paper, we propose an extended vector space model and on this basis put forward an effective semantic similarity measurement method combining content and structure semantics, in which a variety of XML document features impacting similarity measurement, such as term element frequency, term inverse element frequency, semantic weight of tag and level information of the term, are analyzed. In addition, information gain, for clustering quality evaluation are introduced motivated by the fact that collection has no classification information in advance. Experiment results show that proposed similarity method (EVSM_SS) outperforms the content and structure integration measurement based on structure path (VSM_SP) as well as traditional document clustering measurement (CO) in information gain and produce better clustering quality.

关键词： XML

来源：评论

学校读者我要写书评

暂无评论

A Baseline for Early Classification of Time Series in An Open World

A Baseline for Early Classification of Time Series in An Ope...

引用

IEEE Annual International Computer Software and Applications Conference (COMPSAC)

作者： Junwei Lv Xuegang Hu Key Laboratory of Knowledge Engineering with Big Data Ministry of Education Hefei University of Technology Hefei China School of Computer Science and Information Engineering Hefei University of Technology Hefei China

ISBN: (数字)9781665488105

ISBN: (纸本)9781665488112

Early classification of time series aims to accurately predict the class label of a time series as early as possible, which is significant but challenging in many time-sensitive applications. Existing early classification methods hold a basic closed-world assumption that the classifier must have seen the classes of test samples. However, new samples that do not belong to any trained class may appear in the real world. In this paper, we first address the early classification in an open world and design two detectors to identify which known class or unknown class a sample belongs to. Specifically, based on the observed data, an early known-class detector is designed to determine the known-class confidence and an early unknown-class detector is designed to determine the unknown-class confidence according to the Minimum Reliable Length (MRL) and the Weibull distribution of each class. Experimental results evaluated on real-world datasets demonstrate that the proposed model can identify samples of unknown and known classes accurately and early.

关键词： Computational modeling Conferences Time series analysis Detectors Reliability engineering Software Weibull distribution

来源：评论

学校读者我要写书评

暂无评论

More Grounded Image Captioning by Distilling Image-Text Matching Model

More Grounded Image Captioning by Distilling Image-Text Matc...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Yuanen Zhou Meng Wang Daqing Liu Zhenzhen Hu Hanwang Zhang Key Laboratory of Knowledge Engineering with Big Data (Ministry of Education) School of Computer Science and Information Engineering Hefei University of Technology University of Science and Technology of China Nanyang Technological University

ISBN: (数字)9781728171685

ISBN: (纸本)9781728171692

Visual attention not only improves the performance of image captioners, but also serves as a visual interpretation to qualitatively measure the caption rationality and model transparency. Specifically, we expect that a captioner can fix its attentive gaze on the correct objects while generating the corresponding words. This ability is also known as grounded image captioning. However, the grounding accuracy of existing captioners is far from *** improve the grounding accuracy while retaining the captioning quality, it is expensive to collect the word-region alignment as strong *** this end, we propose a Part-of-Speech (POS) enhanced image-text matching model (SCAN[24]): POS-SCAN, as the effective knowledge distillation for more grounded image captioning. The benefits are two-fold: 1) given a sentence and an image, POS-SCAN can ground the objects more accurately than SCAN; 2) POS-SCAN serves as a word-region alignment regularization for the captioner's visual attention module. By showing benchmark experimental results, we demonstrate that conventional image captioners equipped with POS-SCAN can significantly improve the grounding accuracy without strong supervision. Last but not the least, we explore the indispensable Self-Critical Sequence Training (SCST[46]) in the context of grounded image captioning and show that the image-text matching score can serve as a reward for more grounded captioning 1 .

关键词： Visualization Grounding Task analysis Training Measurement Computational modeling Image edge detection

来源：评论

学校读者我要写书评

暂无评论

TransD-based Multi-hop Meta Learning for Few-shot knowledge Graph Completion

TransD-based Multi-hop Meta Learning for Few-shot Knowledge ...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Jindi Li Kui Yu Yuling Li Yuhong Zhang Key Laboratory of Knowledge Engineering with Big Data of Ministry of Education Hefei University of Technology Hefei China School of Computer Science and Information Engineering Hefei University of Technology Hefei China

Few-shot knowledge graph completion (FKGC), which aims to infer missing facts about a relation from only a few reference triples, has recently attracted great attention. The core of solving the FKGC task is to learn a vector representation for each few-shot relation using the corresponding entity represen-tations. To this end, existing models generally enhance entity representations with their direct neighbors. However, a large number of entities have few direct neighbors. Hence, encoding only direct neighborhood is insufficient to obtain satisfactory en-tity representations. In addition, current models typically utilize static embeddings to represent entities, ignoring their diverse semantics, i.e., an entity may show distinct semantics within different few-shot relations. To address these issues, we propose a new FKGC framework, namely TransD-based Multi-hop Meta Learning (TDML). TDML consists of three main components: a multi-hop neighbor encoder to enhance entity representations by aggregating heterogeneous multi-hop neighbors, a transformer encoder to generate the relation meta representations, and a TransD-based relation representation updater that allows each entity to exhibit relation-specific semantics and tune the relation meta representations. Extensive experiments on two public datasets demonstrate that our model outperforms state-of-the-art FKGC methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

LotusX: A Position-Aware XML Graphical Search System with Auto-Completion

LotusX: A Position-Aware XML Graphical Search System with Au...

引用

International Conference on data engineering

作者： Chunbin Lin Jiaheng Lu Tok Wang Ling Bogdan Cautis Key Laboratory of Data Engineering and Knowledge Engineering MOE Renmin University of China China School of Computing National University of Singapore Singapore Télécom Paris Technology France

ISBN: (纸本)9781467300421

The existing query languages for XML (e.g., XQuery) require professional programming skills to be formulated, however, such complex query languages burden the query processing. In addition, when issuing an XML query, users are required to be familiar with the content (including the structural and textual information) of the hierarchical XML, which is diffcult for common users. The need for designing user friendly interfaces to reduce the burden of query formulation is fundamental to the spreading of XML community. We present a twig-based XML graphical search system, called LotusX, that provides a graphical interface to simplify the query processing without the need of learning query language and data schemas and the knowledge of the content of the XML document. The basic idea is that LotusX proposes "position-aware" and "auto-completion" features to help users to create tree-modeled queries (twig pattern) by providing the possible candidates on-the-fly. In addition, complex twig queries (including order sensitive queries) are supported in LotusX. Furthermore, a new ranking strategy and a query rewriting solution are implemented to rank and rewrite the query effectively. We provide an online demo for LotusX system: http://***:8080/LotusX.

关键词： XML database languages Indexes Books Query processing Programming keyword search

来源：评论

学校读者我要写书评

暂无评论

Combining term semantics with content and structure semantics for XML element search results clustering

引用

Journal of Convergence Information Technology 2012年第15期7卷 26-35页

The biggest characteristic of the XML retrieval is able to return the element node results. This paper studies XML element search results clustering and proposes one similarity measurement method based on term semantics, in which the "core" concept between terms is got through latent semantic indexing technology(LSI) and the same time the XML element node content and semantic structure properties(CASS) are combined. In addition, two new performance evaluation methodologies, namely R_ClusterRatio and R_DocuRatio are introduced to evaluate clustering quality. It is motivated by the observations of relevant documents distribution and the fact that the experiment data collection, IEEE CS corpus, do not provide classification information. Experiment results show that proposed similarity method combining term semantics with content and structure semantics integration(LSI-CASS) is feasible, and it produces better clustering quality than LSI-CAS and CASS.

关键词： Semantics

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：