Extractive speech summarization using evaluation metric-related training criteria

The purpose of extractive speech summarization is to automatically select a number of indicative sentences or paragraphs (or audio segments) from the original spoken document according to a target summarization ratio and then concatenate them to form a concise summary. Much work on extractive summarization has been initiated for developing machine-learning approaches that usually cast important sentence selection as a two-class classification problem and have been applied with some success to a number of speech summarization tasks. However, the imbalanced-data problem sometimes results in a trained speech summarizer with unsatisfactory performance. Furthermore, training the summarizer by improving the associated classification accuracy does not always lead to better summarization evaluation performance. In view of such phenomena, we present in this paper an empirical investigation of the merits of two schools of training criteria to alleviate the negative effects caused by the aforementioned problems, as well as to boost the summarization performance. One is to learn the classification capability of a summarizer on the basis of the pair-wise ordering information of sentences in a training document according to a degree of importance. The other is to train the summarizer by directly maximizing the associated evaluation score or optimizing an objective that is linked to the ultimate evaluation. Experimental results on the broadcast news summarization task suggest that these training criteria can give substantial improvements over a few existing summarization methods.     

Home advantage in judo: A study of the world ranking list

Abstract

In 2009, the International Judo Federation established a ranking system (RS) to classify athletes and to distribute the competitor quotas of the Olympic Games. However, the RS does not consider the home advantage. This issue has not been studied in judo, and its implications for the RS have not been determined. The objective was to verify the home advantage in judo in terms of winning a medal or the number of matches won. Therefore, 25 competitions that computed points for the RS in 2009 were analysed. Logistic regression analysis and the Poisson generalised linear model were used for the analyses, which included the relative quality of the athletes. The sample was composed only of athletes who had competed both at home and away. The odds ratio for winning medals was higher for athletes who competed at home for both males and females. The association between the number of matches won and competing at home was significant only for the male athletes. The home advantage was observed in the competitions that used the judo RS. Thus, it is likely that athletes from countries that host competitions using the RS have an advantage in terms of obtaining their Olympic classification.     

Personalized recommendation via user preference matching

Graph-based recommendation approaches use a graph model to represent the relationships between users and items, and exploit the graph structure to make recommendations. Recent graph-based recommendation approaches focused on capturing users’ pairwise preferences and utilized a graph model to exploit the relationships between different entities in the graph. In this paper, we focus on the impact of pairwise preferences on the diversity of recommendations. We propose a novel graph-based ranking oriented recommendation algorithm that exploits both explicit and implicit feedback of users. The algorithm utilizes a user-preference-item tripartite graph model and modified resource allocation process to match the target user with users who share similar preferences, and make personalized recommendations. The principle of the additional preference layer is to capture users’ pairwise preferences, provide detailed information of users for further recommendations. Empirical analysis of four benchmark datasets demonstrated that our proposed algorithm performs better in most situations than other graph-based and ranking-oriented benchmark algorithms.     

Library Ranking Europe: A New Tool

ABSTRACT

The interest to improve library services is worldwide. Standards, various kinds of assessments and customer surveys are used as tools. To be more successful in their business libraries should pay more attention to the customer experience and use qualitative methods in evaluating services. Library Ranking Europe (LRE) is a pilot project which looks at public libraries from a customer perspective. The method is mystery shopping, anonymous visits to libraries. The aim is to create a ranking system that stimulates benchmarking. The ranking system consists of different factors – categories and subcategories – which reflect library services. In the evaluation, every category is scored. The LRE scale generates a ranking system that categorizes libraries according to the scores from one to six stars, from Poor to Exceptional. The system will be developed further but after five years of testing, we find that LRE offers a relatively easy way to compare public libraries in different European countries. It even makes it possible to evaluate and compare libraries in big cities and small villages. The ultimate goal of this method is to enhance quality development.     

SRL-ESA-TextSum: A text summarization approach based on semantic role labeling and explicit semantic analysis

Automatic text summarization attempts to provide an effective solution to today’s unprecedented growth of textual data. This paper proposes an innovative graph-based text summarization framework for generic single and multi document summarization. The summarizer benefits from two well-established text semantic representation techniques; Semantic Role Labelling (SRL) and Explicit Semantic Analysis (ESA) as well as the constantly evolving collective human knowledge in Wikipedia. The SRL is used to achieve sentence semantic parsing whose word tokens are represented as a vector of weighted Wikipedia concepts using ESA method. The essence of the developed framework is to construct a unique concept graph representation underpinned by semantic role-based multi-node (under sentence level) vertices for summarization. We have empirically evaluated the summarization system using the standard publicly available dataset from Document Understanding Conference 2002 (DUC 2002). Experimental results indicate that the proposed summarizer outperforms all state-of-the-art related comparators in the single document summarization based on the ROUGE-1 and ROUGE-2 measures, while also ranking second in the ROUGE-1 and ROUGE-SU4 scores for the multi-document summarization. On the other hand, the testing also demonstrates the scalability of the system, i.e., varying the evaluation data size is shown to have little impact on the summarizer performance, particularly for the single document summarization task. In a nutshell, the findings demonstrate the power of the role-based and vectorial semantic representation when combined with the crowd-sourced knowledge base in Wikipedia.     

大学图书馆水平与大学排名相关性实证研究

选取27所“985大学”和30所“211大学”作为研究对象,构建竞争力评价指标体系,并且通过因子分析对12个指标以及57所大学进行分析,对大学图书馆竞争力的综合排名与大学排名进行相关分析,同时与美国大学进行比较分析,结果表明大学图书馆发展水平与大学竞争力排名呈高度相关。     

基于HITS算法的期刊评价研究

构建了适用于期刊引用网络的HITS(hypertext in-duced topic search)算法,利用2006年的中国科技论文与引文数据库(CSTPCD)分别计算所有及化学类统计源期刊的权威(authority)值与中心(hub)值,并与影响因子进行了对比研究,讨论了HITS算法用于期刊评价的优缺点以及适用范围。     

基于阅读价值的科技文献排序方法研究

科技文献的准备是开展科研工作的必须步骤和重要基础,而当前从电子期刊数据库中检索到的相关文献往往成百上千篇.如何判断一篇文献的阅读价值,并快速准确地获得相关知识,成为科技文献服务方面的一个共性需求.本文针对在科研工作中需要快速对文献按阅读价值进行排序并获得相关知识这一共性需求,以PageRank算法为基础,提出并验证了一种综合考虑文献的内容、期刊、作者、时间等反映文献阅读价值的因素对文献进行排序的PaperRank方法.该方法在得到依据文献阅读价值的排序结果的同时,还可获得在某一问题或领域研究中的重要作者和重要文献等相关知识.     

图书排架方法探究

文章综述了近二十年来我国图书馆采用的各种排架方法以及有关排架方法的研究现状．指出了各种排架方法的优点和存在的问题,展望了未来图书馆书库排架的发展趋势。     

基于改进PageRank算法的引文文献排序方法

通过引文网络的结构特征,有效地识别科学文献的价值并建立某种序关系,为科学评价提供了有价值的参考,也丰富了科学评价的方法。针对传统PageRank算法在引文网络中得到的结果倾向于发表时间久的文献,而不利于发表时间较短但具有学术影响潜力的文献,为了消除这种“不公平”性,将引文间隔时间引入算法中。图书馆与情报学领域的实证研究说明改进算法有效地优化了评价的结果,相对于传统PageRank算法更有利于发现具有潜力的新发表的文献。