Distance learning for MLA’s centennial!

In celebration of the Medical Library Association’s Centennial, their Continuing Education Committee developed a year of distance learning opportunities concerning evidence-based health care. The Centennial Distance Learning Program, as it became known, strove to reach as many members as possible by offering a wide variety of formats, including a teleconference, Web resources, journal clubs, and a suite of traditional CE courses at the annual meeting. This was the first time that MLA had attempted a multi-level distance learning project and it proved to be a rousing success! For more details, visit the ‘EBHC in Action’ Web page on MLANET at: http://www.mlanet.org/education/telecon/index.html .     

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。     

Linear feature extraction for ranking

We address the feature extraction problem for document ranking in information retrieval. We then propose LifeRank, a Linear feature extraction algorithm for Ranking. In LifeRank, we regard each document collection for ranking as a matrix, referred to as the original matrix. We try to optimize a transformation matrix, so that a new matrix (dataset) can be generated as the product of the original matrix and a transformation matrix. The transformation matrix projects high-dimensional document vectors into lower dimensions. Theoretically, there could be very large transformation matrices, each leading to a new generated matrix. In LifeRank, we produce a transformation matrix so that the generated new matrix can match the learning to rank problem. Extensive experiments on benchmark datasets show the performance gains of LifeRank in comparison with state-of-the-art feature selection algorithms.     

Probabilistic relevance ranking for collaborative filtering

Collaborative filtering is concerned with making recommendations about items to users. Most formulations of the problem are specifically designed for predicting user ratings, assuming past data of explicit user ratings is available. However, in practice we may only have implicit evidence of user preference; and furthermore, a better view of the task is of generating a top-N list of items that the user is most likely to like. In this regard, we argue that collaborative filtering can be directly cast as a relevance ranking problem. We begin with the classic Probability Ranking Principle of information retrieval, proposing a probabilistic item ranking framework. In the framework, we derive two different ranking models, showing that despite their common origin, different factorizations reflect two distinctive ways to approach item ranking. For the model estimations, we limit our discussions to implicit user preference data, and adopt an approximation method introduced in the classic text retrieval model (i.e. the Okapi BM25 formula) to effectively decouple frequency counts and presence/absence counts in the preference data. Furthermore, we extend the basic formula by proposing the Bayesian inference to estimate the probability of relevance (and non-relevance), which largely alleviates the data sparsity problem. Apart from a theoretical contribution, our experiments on real data sets demonstrate that the proposed methods perform significantly better than other strong baselines.

Credibility-inspired ranking for blog post retrieval

Credibility of information refers to its believability or the believability of its sources. We explore the impact of credibility-inspired indicators on the task of blog post retrieval, following the intuition that more credible blog posts are preferred by searchers. Based on a previously introduced credibility framework for blogs, we define several credibility indicators, and divide them into post-level (e.g., spelling, timeliness, document length) and blog-level (e.g., regularity, expertise, comments) indicators. The retrieval task at hand is precision-oriented, and we hypothesize that the use of credibility-inspired indicators will positively impact precision. We propose to use ideas from the credibility framework in a reranking approach to the blog post retrieval problem: We introduce two simple ways of reranking the top n of an initial run. The first approach, Credibility-inspired reranking, simply reranks the top n of a baseline based on the credibility-inspired score. The second approach, Combined reranking, multiplies the credibility-inspired score of the top n results by their retrieval score, and reranks based on this score. Results show that Credibility-inspired reranking leads to larger improvements over the baseline than Combined reranking, but both approaches are capable of improving over an already strong baseline. For Credibility-inspired reranking the best performance is achieved using a combination of all post-level indicators. Combined reranking works best using the post-level indicators combined with comments and pronouns. The blog-level indicators expertise, regularity, and coherence do not contribute positively to the performance, although analysis shows that they can be useful for certain topics. Additional analysis shows that a relative small value of n (15–25) leads to the best results, and that posts that move up the ranking due to the integration of reranking based on credibility-inspired indicators do indeed appear to be more credible than the ones that go down.     

Efficient algorithms for ranking with SVMs

RankSVM (Herbrich et al. in Advances in large margin classifiers. MIT Press, Cambridge, MA, 2000; Joachims in Proceedings of the ACM conference on knowledge discovery and data mining (KDD), 2002) is a pairwise method for designing ranking models. SVMLight is the only publicly available software for RankSVM. It is slow and, due to incomplete training with it, previous evaluations show RankSVM to have inferior ranking performance. We propose new methods based on primal Newton method to speed up RankSVM training and show that they are 5 orders of magnitude faster than SVMLight. Evaluation on the Letor benchmark datasets after complete training using such methods shows that the performance of RankSVM is excellent.     

Neural ranking models for document retrieval

Information Retrieval Journal - Ranking models are the main components of information retrieval systems. Several approaches to ranking are based on traditional machine learning algorithms using a...     

徽州文书著录项目构成设计

编制徽州文书目录是徽州文书整理工作的重要一环。文章根据徽州文书内容和形式的特点,参照《文献著录总则》制定的著录规则,将徽州文书目录的著录项目归纳设计为九大项:编号项、题名项、类别项、事主项、年代项、地点项、细节记载项、载体形态项以及附注项。     

Mind the Gap! Making the Leap to Reach Distance Students Through On-Campus Events

When a mid-sized library at a private university held its first robust research-support event, a huge portion of the student body was noticeably absent – the distance population. The ACRL Standards for Distance Learning Library Services affirms that distance learners are entitled to the same services and resources as on-campus learners. This means that “service excellence in distance librarianship” should include conducting outreach programs for distance learners that parallels outreach programs for on-campus learners. This case study tracks the process of rethinking an on-campus event to incorporate distance learners. It is designed to communicate how a shift in thinking can create opportunities for outreach experiences by transforming existing events and/or extending programs the first time they are made available.     

A new national standard for electronic documents

This paper analyzes the recently approved GOST R 7. 095–2015. Electronic Documents. Main Types, Output Information, and Technological Characteristics national standard that considers an electronic document as a component of librarian and archival funds, as well as formulating the signs that permit an electronic object to be attributed to the class of documents. The type of an electronic document determines its functionality, which in turn causes the technological requirements for the material implementation of the document (in particular, the requirements for formats). Due to the specificity of data processing in the electronic environment, an electronic document exists as many equivalent implementations and any work with it, including displaying, is the continuous creation of these implementations. In this regard, the technological operation of copying leads not to creating a document of a new type (a “copy”) but only to the origin of a new implementation that is equivalent to any other. Hence, there is a need for a set of identification characteristics (attributes) for electronic documents.     

Let Me Show You How It's Done! Desktop Sharing for Distance Learning from the D. Samuel Gottesman Library

Due to the proliferation of electronic resources, fewer users visit the library. Traditional classroom instruction and in-person consultations are no longer sufficient in assisting library users. Librarians are constantly seeking new ways to interact with patrons and facilitate efficient use of electronic resources. This article describes the development, implementation, and evaluation of a project in which desktop-sharing software was used to reach out to users at remote locations. Various ways of using this tool are described, and challenges and implications for future expansion are discussed.     

An environment for processing images of historical documents

This paper presents an environment for acquisition, filtering, compression and storage of images of historical documents.     

二次学术文献编辑素质问题探讨

二次学术文献是专门搜集、梳理和检阅并控制一次学术文献的文献,其意义和价值还在于弥补一次学术文献的缺陷.二次学术文献编辑的素质要求,既有一般编辑的素质要求,更有自己的特殊素质要求.关于二次学术文献编辑素质的问题,至今还很少有人问津.作此探讨,目的是为了引起人们对此问题的关注.     

A probability ranking principle for interactive information retrieval

The classical Probability Ranking Principle (PRP) forms the theoretical basis for probabilistic Information Retrieval (IR) models, which are dominating IR theory since about 20 years. However, the assumptions underlying the PRP often do not hold, and its view is too narrow for interactive information retrieval (IIR). In this article, a new theoretical framework for interactive retrieval is proposed: The basic idea is that during IIR, a user moves between situations. In each situation, the system presents to the user a list of choices, about which s/he has to decide, and the first positive decision moves the user to a new situation. Each choice is associated with a number of cost and probability parameters. Based on these parameters, an optimum ordering of the choices can the derived—the PRP for IIR. The relationship of this rule to the classical PRP is described, and issues of further research are pointed out.

DataNet: A model source for local documents

DataNet, a database produced by the Metro Chicago Information Center, is a unique resource for Chicago area government, regional government, and community organization information. It has a dual role as both a traditional source of bibliographic information and as a clearinghouse for names, addresses, and phone numbers of local agencies and information producers. In addition, DataNet could serve as a model local information database for other municipalities or local regional governments.     

A synergetic paradigm for the scientific study of documents

Document theory is the least explored area of study about documents. It lags significantly behind applied document research, which summarizes various document processing practices that have accumulated for thousands of years. This problem has recently been complicated by the rise of so-called general document theories. The boundaries of the document concept have become blurred due to the development of parallel areas of study and their forced differentiation into “classic” and “library” document science. In addition, knowledge about objects that are referred to as documents that can neither be properly integrated nor applied in practice is being developed. This situation is mainly due to the lack of attention that is paid by document scientists to the theoretical and methodological issues of document science. This paper reviews the origins, nature, and the social roles of documents from the perspective of a synergetic paradigm and has the goal of constructing a synergetic document theory.     

Planning for Distance Learning

Abstract

The article examines the role that student support services plays in planning a distance learning program, especially the services offered by a university library. The content of the paper is based on the experience the author acquired as a member of Texas Tech University's Distance Learning Council. The Council's efforts to plan a program that will include strong support from the Library are discussed.     

The uncertain representation ranking framework for concept-based video retrieval

Concept based video retrieval often relies on imperfect and uncertain concept detectors. We propose a general ranking framework to define effective and robust ranking functions, through explicitly addressing detector uncertainty. It can cope with multiple concept-based representations per video segment and it allows the re-use of effective text retrieval functions which are defined on similar representations. The final ranking status value is a weighted combination of two components: the expected score of the possible scores, which represents the risk-neutral choice, and the scores’ standard deviation, which represents the risk or opportunity that the score for the actual representation is higher. The framework consistently improves the search performance in the shot retrieval task and the segment retrieval task over several baselines in five TRECVid collections and two collections which use simulated detectors of varying performance.