Reading comprehension tasks are commonly used for developing students' reading ability. In order to adaptively recommend reading comprehension materials to students engaged in computerized testing, the information in an item bank (a collection of test items stored in a dataset) must be effectively indexed. Familiarity with the topics present in…

In the last decade e-lecturing has become more and more popular. The amount of lecture video data on the "World Wide Web" (WWW) is growing rapidly. Therefore, a more efficient method for video retrieval in WWW or within large lecture video archives is urgently needed. This paper presents an approach for automated video indexing and video…

The purpose of this research is to simulate the manual process of assigning descriptors to magazine articles by machine, to investigate how successful automated assignment of descriptors to a heterogeneous text collection is when a text classifier is trained based upon a small set of manually classified example texts, and to test performance of…

The SALOMON project automatically summarizes Belgian criminal cases to improve access to existing and future court decisions. This article gives background information about the texts of the cases and describes the output, design models, and architecture of the SALOMON system. Evaluation of 700 criminal cases demonstrates that the algorithms have…

Describes an alternative method for indexing images in an image database. The method consists of manually indexing a selected reference image, and then using retrieval by graphical content to automatically transfer the manually assigned index terms from the reference image to the images to be indexed. (AEF)

Most existing automatic content analysis and indexing techniques are based on work frequency characteristics applied largely in an ad hoc manner. Contradictory requirements arise in this connection, in that terms exhibiting high occurrence frequencies in individual documents are often useful for high recall performance (to retrieve many relevant…

Work has been performed on a fully automated approach for the general categorization of documents based on a training set of document titles and abstracts and journal-level indexing of the journals in which the documents are published. The goal of this research is to automatically index documents using a consistent, timely set of controlled…

The mathematical model proposed describes a computerized bibliographic information system which includes a method--document learning--of improving the set of index terms assigned to a document representative. Inputs to the information system (index terms and query), relevance feedback, and assumptions concerning the model are discussed.…

Describes the development and outcome of a cooperative computerization effort involving nine public and university museums. The discussion covers the project goals, data development and analysis, and contributions resulting form the project. Appendices provide the system data fields used and a comparison between automation of library and museum…

Presents a metric for comparing the performance of common classes of Internet information retrieval tools, including human indexed catalogs of Web resources and automatically indexed databases of Web pages. The benefit of the proposed metric is that it is relevance-based, and it facilitates the comparison of the performance of different classes of…

Improvements in the technology associated with the information sciences will have their primary potential impact on the distribution of costs, information flow level, information availability, and use among information channels. This improvement implied not only a capability to perform a given function, but a lower cost. For example, the trend…