检索结果-内蒙古大学图书馆

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Guo, Shasha Liao, Lizi Zhang, Jing 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 Singapore Management University Singapore

ISBN: (纸本)9798891761643

Conversational Question Generation (CQG) enhances the interactivity of conversational question-answering systems in fields such as education, customer service, and entertainment. However, traditional CQG, focusing primarily on the immediate context, lacks the conversational foresight necessary to guide conversations toward specified conclusions. This limitation significantly restricts their ability to achieve conclusion-oriented conversational outcomes. In this work, we redefine the CQG task as Conclusion-driven Conversational Question Generation (CCQG) by focusing on proactivity, not merely reacting to the unfolding conversation but actively steering it towards a conclusion-oriented question-answer pair. To address this, we propose a novel approach, called Proactive Conversational Question Planning with self-Refining (PCQPR). Concretely, by integrating a planning algorithm inspired by Monte Carlo Tree Search (MCTS) with the analytical capabilities of large language models (LLMs), PCQPR predicts future conversation turns and continuously refines its questioning strategies. This iterative self-refining mechanism ensures the generation of contextually relevant questions strategically devised to reach a specified outcome. Our extensive evaluations demonstrate that PCQPR significantly surpasses existing CQG methods, marking a paradigm shift towards conclusion-oriented conversational question-answering systems. © 2024 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

MFSV: A truthfulness determination approach for fact statements

MFSV: A truthfulness determination approach for fact stateme...

引用

18th International Conference on database Systems for Advanced Applications, DASFAA 2013

作者： Wang, Teng Zhu, Qing Wang, Shan Key Laboratory of the Ministry of Education for Data Engineering and Knowledge Engineering Renmin University of China Beijing China School of Information Renmin University of China Beijing China

ISBN: (纸本)9783642374494

How to determine the truthfulness of a piece of information becomes an increasingly urgent need for users. In this paper, we propose a method called MFSV, to determine the truthfulness of fact statements. We first calculate the similarity between a piece of related information and the target fact statement and capture the credibility ranking of the related information through combining importance ranking and popularity ranking. Based on these, contributions of a piece of related information to the truthfulness determination is derived. Then we propose two methods to determine the truthfulness of the target fact statement. At last, we run comprehensive experiments to show MFSV's availability and high accuracy. © Springer-Verlag 2013.

关键词： Computers

来源：评论

学校读者我要写书评

暂无评论

Semi-automatic online tagging with K-Medoid clustering

Semi-automatic online tagging with K-Medoid clustering

引用

作者： Hu, He Du, Xiaoyong School of Information Renmin University of China Key Laboratory of Data Engineering and Knowledge Engineering MoE No. 59 Zhongguancun St. Beijing100872 China

Online tagging is crucial for the acquisition and organization of web knowledge. We present TYG (Tag-as-You-Go) in this paper, a web browser extension for online tagging of personal knowledge on standard web pages. We investigate an approach to combine a K-Medoid-style clustering algorithm with the user input to achieve semi-automatic web page annotation. The annotation process supports user-defined tagging schema and comprises an automatic mechanism that is built upon clustering techniques, which can automatically group similar HTML DOM nodes into clusters corresponding to the user specification. TYG is a prototype system illustrating the proposed approach. Experiments with TYG show that our approach can achieve both efficiency and effectiveness in real world annotation scenarios. © 2014 World Scientific Publishing Company.

关键词： Websites

来源：评论

学校读者我要写书评

暂无评论

Multi-verifier: A novel method for fact statement verification

Multi-verifier: A novel method for fact statement verificati...

引用

15th Asia-Pacific Web Conference on Web Technologies and Applications, APWeb 2013

ISBN: (纸本)9783642374005

Untruthful information spreads on the web, which may mislead users or have a negative impact on user experience. In this paper, we propose a method called Multi-verifier to determine the truthfulness of a fact statement. The basic idea is that whether a fact statement is truthful or not depends on the information related to the fact statement. We utilize a popular search engine to collect the top-n search results that are most related to the target fact statement. We then propose support score to measure the extent to which a search result supports the fact statement, and we make use of credibility ranking to rank the search results. At last, we combine the support score and credibility ranking value of a search result to evaluate its contribution to a fact statement determination. Based on the contributions of the search results, we determine the fact statement. Our proposals are evaluated by experiments and results show availability and high precision of the proposed method. © 2013 Springer-Verlag.

关键词： Search engines

来源：评论

学校读者我要写书评

暂无评论

QueryAccelerator: A SQL converter capturing and transforming the slow plan

引用

Neurocomputing 2025年 645卷

作者： Yang, Shaocong Wang, Ning Zeng, Qixiong Zhou, Anshun School of Computer Science & Technology Beijing Jiaotong University Beijing100044 China Beijing Key Laboratory of Traffic Data Analysis and Mining Beijing Jiaotong University Beijing100044 China School of Communication and Information Engineering Nanjing University of Posts and Telecommunications Nanjing210003 China

For slow queries, rewriting is a prerequisite for effective query optimization in database systems. To convert a slow query into a more efficient SQL, a suitable rewrite rule application sequence is required. However, existing rewriting methods have the problems of insufficient representation of query features, too large exploration space and lack of early avoidance of error queries, which limits rewriting performance, benefits and accuracy, therefore affects the efficiency of query execution. In this paper, we propose QueryAccelerator, a slow query rewriting framework that explores suitable rule application sequences based on execution plans. We use the deep reinforcement learning to capture the optimizable space within slow query plans, and use rule categories as the exploration granularity to reduce the search space of rule application paths and avoid falling into local optimality. Additionally, to improve the accuracy of rewritten queries, we propose to reduce the rewriting benefits along paths with error nodes during the model exploration process, so as to avoid semantically inequivalent rewritten queries. Experimental results on slow queries written by real developers on LeetCode show that, compared with state-of-the-art query rewriting techniques, QueryAccelerator can not only optimize more slow queries, but also bring more performance improvements. © 2025 Elsevier B.V.

关键词： Query languages

来源：评论

学校读者我要写书评

暂无评论

FindCredPg: A novel method to find credible pages based on trust web graph

引用

14th Asia Pacific Web Technology Conference, APWeb 2012

作者： Wang, Teng Zhu, Qing Wang, Shan Liang, Jingfan Key Laboratory of the Ministry of Education for Data Engineering and Knowledge Engineering Renmin University of China Beijing China School of Information Renmin University of China Beijing China

ISBN: (纸本)9783642292521

Finding credible pages is a challenging problem on the Web. Our key observation in this paper is that credible pages usually link to credible content-related pages, which is different from a normal page usually links to normal pages in spam page detection. We propose a novel method to find credible pages based on the trust web graph we define. This method first measures the content correlation between pages connected by hyperlinks, then it combines web link structure with content correlation value of pages to build a trust web graph. At last, credible pages are found successfully by using trust relation of vertices on the trust web graph. We construct a real-world data set by crawling millions of pages on the web and run a set of experiments on this data set. Experiment results show that the accuracy of this method is near 80% and the efficiency is higher. © 2012 Springer-Verlag Berlin Heidelberg.

关键词： Hypertext systems

来源：评论

学校读者我要写书评

暂无评论

Can web news media sentiments improve stock trading signal prediction? 18

Can web news media sentiments improve stock trading signal p...

引用

18th Pacific Asia Conference on Information Systems, PACIS 2014

作者： Lin, Nana Xu, Wei Zhang, Xinwei Lv, Siqi School of Information Renmin University of China Beijing China Key Laboratory of Data Engineering and Knowledge Engineering Renmin University of China School of Information Beijing China

The technical analysis and machine learning have been integrated in stock trading signal forecasting. And it has been proved that there are some weaknesses in technical analysis because of the complex environment in the stock market. In our prediction system, web news media sentiment analysis is regarded as a supplementary way to cover the shortage of technical analysis. It is considered to bring the stock market sentiment which reflects the subjective information of investors into the prediction system. Web news media sentiment indicators (WNMS) are designed to bring the information about stock market sentiment in our system. The WNMS is generated by analyzing the variance of sentiment elements from the news in the Stock Timely Rain Sector of Sina Finance and Economics Website and it is imported into the prediction system as features combined with common feature indicators (CFI). GMKL is applied to establish the relationship between the trading signals generated by piecewise linear representation (PLR) and the features of the trading signals (SCFI). Comparative experiments are adopted in nine stocks from Shanghai and Shenzhen Stock Exchange to determine the effect of PLR-GMKL and WNMS in prediction. From the aspects of the prediction accuracy and the profit, the final comparative results show that the PLR-GMKL model performs better than the PLR-WSVM model. And the prediction system performs best when adding WNMS into features and using PLRGMKL model.

关键词： Financial markets

来源：评论

学校读者我要写书评

暂无评论

Tracer: Enforcing Mandatory Access Control in commodity OS with the support of light-weight intrusion detection and tracing 11

Tracer: Enforcing Mandatory Access Control in commodity OS w...

引用

6th International Symposium on Information, Computer and Communications Security, ASIACCS 2011

作者： Shan, Zhiyong Wang, Xin Chiueh, Tzi-Cker Key Laboratory of Data Engineering and Knowledge Engineering Renmin University MOE China Stony Brook University United States Industrial Technology Research Institute Taiwan

ISBN: (纸本)9781450305648

Enforcing a practical Mandatory Access Control (MAC) in a commercial operating system to tackle malware problem is a grand challenge but also a promising approach. The firmest barriers to apply MAC to defeat malware programs are the incompatible and unusable problems in existing MAC systems. To address these issues, we start our work by analyzing the technical details of 2,600 malware samples one by one and performing experiments over two types of MAC enforced operating systems. Based on the preliminary studies, we design a novel MAC model incorporating intrusion detection and tracing in a commercial operating system, named Tracer, in order to disable malware on hosts while offering good compatibility to existing software and good usability to common users who are not system experts. The model conceptually consists of three actions: detecting, tracing and restricting suspected intruders. One novelty is that it leverages light-weight intrusion detection and tracing techniques to automate security label configuration that is widely acknowledged as a tough issue when applying a MAC system in practice. The other is that, rather than restricting information flow as a traditional MAC does, it traces intruders and restricts only their critical malware behaviors, where intruders represent processes and executables that are potential agents of a remote attacker. Our prototyping and experiments on Windows show that Tracer can effectively defeat all malware samples tested via blocking malware behaviors while not causing a significant compatibility problem. Copyright 2011 ACM.

关键词： Malware

来源：评论

学校读者我要写书评

暂无评论

SGSH: Stimulate Large Language Models with Skeleton Heuristics for knowledge Base Question Generation

SGSH: Stimulate Large Language Models with Skeleton Heuristi...

引用

2024 Findings of the Association for Computational Linguistics: NAACL 2024

作者： Guo, Shasha Liao, Lizi Zhang, Jing Wang, Yanling 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 Singapore Management University Singapore Zhongguancun Laboratory China

ISBN: (纸本)9798891761193

knowledge base question generation (KBQG) aims to generate natural language questions from a set of triplet facts extracted from KB. Existing methods have significantly boosted the performance of KBQG via pre-trained language models (PLMs) thanks to the richly endowed semantic knowledge. With the advance of pre-training techniques, large language models (LLMs) (e.g., GPT-3.5) undoubtedly possess much more semantic knowledge. Therefore, how to effectively organize and exploit the abundant knowledge for KBQG becomes the focus of our study. In this work, we propose SGSH - a simple and effective framework to Stimulate GPT-3.5 with Skeleton Heuristics to enhance KBQG. The framework incorporates "skeleton heuristics", which provides more fine-grained guidance associated with each input to stimulate LLMs to generate optimal questions, encompassing essential elements like the question phrase and the auxiliary verb. More specifically, we devise an automatic data construction strategy leveraging ChatGPT to construct a skeleton training dataset, based on which we employ a soft prompting approach to train a BART model dedicated to generating the skeleton associated with each input. Subsequently, skeleton heuristics are encoded into the prompt to incentivize GPT-3.5 to generate desired questions. Extensive experiments demonstrate that SGSH derives the new state-of-the-art performance on the KBQG tasks. The code is now available on Github. © 2024 Association for Computational Linguistics.

关键词： knowledge based systems

来源：评论

学校读者我要写书评

暂无评论

INK: A cloud-based system for efficient top-k interval keyword search 14

INK: A cloud-based system for efficient top-k interval keywo...

引用

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

作者： Li, Rui Zhang, Xiao Zhou, Xin Wang, Shan Key Laboratory of Data Engineering and Knowledge Engineering of the Ministry of Education Renmin University of China Beijing China School of Information Renmin University of China Beijing China

ISBN: (纸本)9781450325981

It is insufficient to search temporal text by only focusing on either time attribute or keywords today as we pay close attention to the evolution of event with time. Both temporal and textual constraints need to be considered in one single query, called Top-k Interval keyword Query (TIKQ). In this paper, we presents a cloud-based system named INK that supports efficient execution of TIKQs with appropriate effectiveness on Hadoop and HBase. In INK, an Adaptive Index Selector (AIS) is devised to choose the better execution plan for various TIKQs adaptively based on the proposed cost model, and leverage two novel hybrid index modules (TriI and IS-Tree) to combine keyword and interval filtration seamlessly.

关键词： Search engines

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：