检索结果-内蒙古大学图书馆

Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024

作者： Guo, Shasha Zhang, Jing Ke, Xirui Li, Cuiping Chen, Hong School of Information Renmin University of China Beijing China Key Laboratory of Data Engineering and Knowledge Engineering of Ministry of Education China

ISBN: (纸本)9782493814104

Previous methods on knowledge base question generation (KBQG) primarily focus on refining the quality of a single generated question. However, considering the remarkable paraphrasing ability of humans, we believe that diverse texts can express identical semantics through varied expressions. The above insights make diversifying question generation an intriguing task, where the first challenge is evaluation metrics for diversity. Current metrics inadequately assess the aforementioned diversity. They calculate the ratio of unique n-grams in the generated question, which tends to measure duplication rather than true diversity. Accordingly, we devise a new diversity evaluation metric, which measures the diversity among top-k generated questions for each instance while ensuring their relevance to the ground truth. Clearly, the second challenge is how to enhance diversifying question generation. To address this challenge, we introduce a dual model framework interwoven by two selection strategies to generate diverse questions leveraging external natural questions. The main idea of our dual framework is to extract more diverse expressions and integrate them into the generation model to enhance diversifying question generation. Extensive experiments on widely used benchmarks for KBQG show that our approach can outperform pre-trained language model baselines and text-davinci-003 in diversity while achieving comparable performance with ChatGPT. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

SeaDATE: Remedy Dual-Attention Transformer with Semantic Alignment via Contrast Learning for Multimodal Object Detection

引用

IEEE Transactions on Circuits and Systems for Video Technology 2024年第5期35卷 4713-4726页

作者： Dong, Shuhan Xie, Weiying Yang, Danian Tian, Jiayuan Li, Yunsong Zhang, Jiaqing Lei, Jie The State Key Laboratory of Integrated Services Networks Xidian University Xi’an710071 China School of Electrical and Data Engineering University of Technology Sydney Sydney Australia

Multimodal object detection leverages diverse modal information to enhance the accuracy and robustness of detectors. Due to its ability to capture long-range dependencies, the Transformer model provides a powerful mechanism for integrating multimodal features during feature extraction. This capability significantly enhances the accuracy of multimodal object detection by addressing the limitations of local feature extraction inherent in traditional methods. However, current methods merely stack Transformer-guided fusion techniques without exploring their capability to extract features at various depth layers of network, thus limiting the improvements in detection performance. In this paper, we introduce an accurate and efficient multimodal object detection method named SeaDATE. Initially, we propose a novel dual attention Feature Fusion (DTF) module that, under Transformer’s guidance, integrates local and global information through a dual attention mechanism, strengthening the fusion of modal features from orthogonal perspectives using spatial and channel tokens. Meanwhile, our theoretical analysis and empirical validation demonstrate that the Transformer-guided fusion method, treating images as sequences of pixels for fusion, performs better on shallow features’ detail information compared to deep semantic information. To address this, we designed a contrastive learning (CL) module aimed at learning features of multimodal samples, remedying the shortcomings of Transformer-guided fusion in extracting deep semantic features, and effectively utilizing cross-modal information. Extensive experiments and ablation studies on the FLIR, LLVIP, and M3FD datasets have proven our method to be effective, achieving state-of-the-art detection performance. ©1991-2012 IEEE.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

DSM: Question Generation over knowledge Base via Modeling Diverse Subgraphs with Meta-learner

DSM: Question Generation over Knowledge Base via Modeling Di...

引用

2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022

作者： Guo, Shasha Zhang, Jing Wang, Yanling Zhang, Qianyi Li, Cuiping Chen, Hong School of Information Renmin University of China Beijing China Key Laboratory of Data Engineering and Knowledge Engineering of Ministry of Education China

Existing methods on knowledge base question generation (KBQG) learn a one-size-fits-all model by training together all subgraphs without distinguishing the diverse semantics of subgraphs. In this work, we show that making use of the past experience on semantically similar subgraphs can reduce the learning difficulty and promote the performance of KBQG models. To achieve this, we propose a novel approach to model diverse subgraphs with meta-learner (DSM). Specifically, we devise a graph contrastive learning-based retriever to identify semantically similar subgraphs, so that we can construct the semantics-aware learning tasks for the meta-learner to learn semantics-specific and semantics-agnostic knowledge on and across these tasks. Extensive experiments on two widely-adopted benchmarks for KBQG show that DSM derives new state-of-the-art performance and benefits the question answering tasks as a means of data augmentation. Codes and datasets are available online. © 2022 Association for Computational Linguistics.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

COP: Privacy-preserving multidimensional partition in DAS paradigm 09

COP: Privacy-preserving multidimensional partition in DAS pa...

引用

2009 International Conference on Extending database Technology/International Conference on database Theory Workshops, EDBT/ICDT '09

作者： Wang, Jieping Du, Xiaoyong Wang, Haocong Yang, Pingping Key Laboratory of Data Engineering and Knowledge Engineering MOE China School of Information Renmin University of China Beijing 100872 China

ISBN: (纸本)9781605586502

database-as-a-Service (DAS) is an emerging database management paradigm wherein partition based index is an effective way to querying encrypted data. However, previous research either focuses on one-dimensional partition or ignores multidimensional data distribution characteristic, especially sparsity and locality. In this paper, we propose Cluster based Onion Partition (COP), which is designed to decrease both false positive and dead space at the same time. Basically, COP is composed of two steps. First, it partition covered space level by level, which is like peeling of onion;second, at each level, a clustering algorithm based on local density is proposed to achieve local optimal secure partition. Extensive experiments on real dataset and synthetic dataset show that COP is a secure multidimensional partition with much less efficiency loss than previous top down or bottom up counterparts. Copyright 2009 ACM.

关键词： database systems

来源：评论

学校读者我要写书评

暂无评论

Efficient Duplicate Detection on Cloud Using a New Signature Scheme

Efficient Duplicate Detection on Cloud Using a New Signature...

引用

12th International Conference on Web-Age Information Management

作者： Rong, Chuitian Lu, Wei Du, Xiaoyong Zhang, Xiao Key Labs. of Data Engineering and Knowledge Engineering MOE China School of Information Renmin University of China China Shanghai Key Laboratory of Intelligent Information Processing China

ISBN: (纸本)9783642235344;9783642235351

Duplicate detection has been well recognized as a crucial task to improve the quality of data. Related work on this problem mainly aims to propose efficient approaches over a single machine. However, with increasing volume of the data, the performance to identify duplicates is still far from satisfactory. Hence, we try to handle the problem of duplicate detection over MapReduce, a share-nothing paradigm. We argue the performance of utilizing MapReduce to detect duplicates mainly depends on the number of candidate record pairs. In this paper, we proposed a new signature scheme with new pruning strategy over MapReduce to minimize the number of candidate record pairs. Our experimental results over both real and synthetic datasets demonstrate that our proposed signature based method is efficient and scalable.

关键词： duplicate detection MapReduce Cloud

来源：评论

学校读者我要写书评

暂无评论

Maintaining materialized relations incrementally to improve performance of ontology query

Maintaining materialized relations incrementally to improve ...

引用

7th International Conference on Web-Age Information Management Workshops, WAIM 2006

作者： Li, Man Du, Xiaoyong Wang, Shan School of Information Renmin University of China China Key Laboratory of Data Engineering and Knowledge Engineering MOE 100872 Beijing China

ISBN: (纸本)0769527051

For ontology-based applications, the efficiency of ontology query is vital. Different from existing approaches, the paper improves performance of ontology query by materializing some derived relations. Experimental results show that the integrated performance of ontology query can be improved greatly by maintaining materialized relations and the materialized relations technique has good scalability. Here the challenge is how to maintain the materialized relations incrementally with the update of ontologies. Because transitive relations are in common use in ontology, the paper proposes a novel algorithm for maintaining transitive materialized relations incrementally based on a special weighted materialized relation transitive graph, which can solve the coexistence problem of multiple derived paths better and proves the correctness of the algorithm. © 2006 IEEE.

关键词： Ontology

来源：评论

学校读者我要写书评

暂无评论

Search result diversification based on hierarchical intents 15

Search result diversification based on hierarchical intents

引用

24th ACM International Conference on Information and knowledge Management, CIKM 2015

作者： Hu, Sha Dou, Zhicheng Wang, Xiaojie Sakai, Tetsuya Wen, Ji-Rong Beijing Key Laboratory of Big Data Management and Analysis Methods China Key Laboratory of Data Engineering and Knowledge Engineering MOE China School of Information Renmin University of China China Waseda University Japan

ISBN: (纸本)9781450337946

A large percentage of queries issued to search engines are broad or ambiguous. Search result diversification aims to solve this problem, by returning diverse results that can fulfill as many different information needs as possible. Most existing intent-aware search result diversification algorithms formulate user intents for a query as a flat list of subtopics. In this paper, we introduce a new hierarchical structure to represent user intents and propose two general hierarchical diversification models to leverage hierarchical intents. Experimental results show that our hierarchical diversification models outperform state-of-the-art diversification methods that use traditional flat subtopics. © 2015 ACM.

关键词： Search engines

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

WATuning:A Workload-Aware Tuning System with Attention-Based Deep Reinforcement Learning

引用

Journal of Computer Science & Technology 2021年第4期36卷 741-761页

作者： Jia-Ke Ge Yan-Feng Chai Yun-Peng Chai Key Laboratory of Data Engineering and Knowledge Engineering of Ministry of Education Renmin University of China Beijing 100872China School of Information Renmin University of ChinaBeijing 100872China College of Computer Science and Technology Taiyuan University of Science and TechnologyTaiyuan 030027China

Configuration tuning is essential to optimize the performance of systems(e.g.,databases,key-value stores).High performance usually indicates high throughput and low *** present,most of the tuning tasks of systems are performed artificially(e.g.,by database administrators),but it is hard for them to achieve high performance through tuning in various types of systems and in various *** recent years,there have been some studies on tuning traditional database systems,but all these methods have some *** this article,we put forward a tuning system based on attention-based deep reinforcement learning named WATuning,which can adapt to the changes of workload characteristics and optimize the system performance efficiently and ***,we design the core algorithm named ATT-Tune for WATuning to achieve the tuning task of *** algorithm uses workload characteristics to generate a weight matrix and acts on the internal metrics of systems,and then ATT-Tune uses the internal metrics with weight values assigned to select the appropriate ***,WATuning can generate multiple instance models according to the change of the workload so that it can complete targeted recommendation services for different types of ***,WATuning can also dynamically fine-tune itself according to the constantly changing workload in practical applications so that it can better fit to the actual environment to make *** experimental results show that the throughput and the latency of WATuning are improved by 52.6%and decreased by 31%,respectively,compared with the throughput and the latency of CDBTune which is an existing optimal tuning method.

关键词： attention mechanism auto-tuning system reinforcement learning(RL) workload-aware

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：