Gregory R. Crane

Disambiguating Geographic Names in a Historical Digital Library

Geographic interfaces provide natural, scalable visualizationss for many digital library collections, but the wide range of data in digital libraries presents some particular problems for identifying and disambiguating place names. We describe the toponym-disambiguation system in the Perseus digital library and evaluate its performance. Name categorization varies significantly among different types of documents, but toponym disambiguation performs at a high level of precision and recall with a gazetteer an order of magnitude larger than most other applications.

Evaluating hypermedia and learning: methods and results from the Perseus Project

The Perseus Project has developed a hypermedia corpus of materials related to the ancient Greek world. The materials include a variety of texts and images, and tools for using these materials and navigating the sytem. Results from a three-year evaluation of Perseus use in a variety of college settings are described. The evaluation assessed both this particular system and the application of the technological genre to information management and to learning. The evaluation used a variety of methods to address questions about learning and teaching with hypermedia and to guide the development of early versions of the system. Results illustrate that such environments offer potential for accelerating learning and for supporting new types of learning and teaching; that students and instructors must develop new strategies for learning and teaching with such technology; and that institutions must develop infrastructural support for such technology. The results also illustrate the importance of well-designed interfaces and different types of assignments on user performance.

The challenge of virginia banks: an evaluation of named entity analysis in a 19th-century newspaper collection

This paper evaluates automatic extraction of ten named entity classes from a 19th century newspaper, the Civil War years of the Richmond Times Dispatch, digitized with IMLS support by the University of Richmond. This paper analyzes success with ten categories of entities prominent in these newspapers and the particular problems that these classes of named entities raise. Personal and place names are familiar but some more important categories (such as ship names and military units) illustrate some of the challenges that named entity identification confronts as it evolves into a fundamental tool not only for automatic metadata generation but also for searching and browsing as well. We conclude by suggesting the kinds of knowledge sources that digital libraries need to assemble as part of their machine readable reference collections to support named entity identification as a core service

The 3D vase museum: a new approach to context in a digital library

We present a new approach to displaying and browsing a digital library collection, a set of Greek vases in the Perseus digital library. Our design takes advantage of three-dimensional graphics to preserve context even while the user focuses in on a single item. In a typical digital library user interface, a user can either get an overview for context or else see a single selected item, sacrificing the context view. In our 3D Vase Museum, the user can navigate seamlessly from a high level scatterplot-like plan view to a perspective overview of a subset of the collection, to a view of an individual item, to retrieval of data associated with that item, all within the same virtual room and without any mode change or special command. We present this as an example of a solution to the problem of focus-plus-context in information visualization. We developed 3D models from the 2D photographs in the collection and placed them in our 3D virtual room. We evaluated our approach by comparing it to the conventional interface in Perseus using tasks drawn from archaeology courses and found a clear improvement. Subjects who used our 3D Vase Museum performed the tasks 33% better and did so nearly three times faster.

Towards a cultural heritage digital library

We survey research areas relevant to cultural heritage digital libraries. The emerging National Science Digital Library promises to establish the foundation on which those of us beyond the scientific and engineering community will likely build. We thus articulate the particular issues that we have encountered in developing cultural heritage collections. We provide a broad overview of audiences, collections, and services.

Building a digital library: the Perseus project as a case study in the humanities

This paper outlines some of our preliminary findings in the PerseusProject, an on-going digital library on ancient Greek culture thathas been under development since 1987.

Improving OCR accuracy for classical critical editions

This paper describes a work-flow designed to populate a digital library of ancient Greek critical editions with highly accurate OCR scanned text. While the most recently available OCR engines are now able after suitable training to deal with the polytonic Greek fonts used in 19th and 20th century editions, further improvements can also be achieved with postprocessing. In particular, the progressive multiple alignment method applied to different OCR outputs based on the same images is discussed in this paper.

The impact of digital libraries on cognitive processes: psychological issues of hypermedia

Abstract Digital library research has focused on the construction of large-scale databases that provide users with hypermedia search and examination tools. Digital library construction has resulted in impressive, albeit sometimes overwhelming content, in a multimedia environment. As such, research should turn to examining the role of the human processor in digital library experiences. Cognitive psychologists have examined the comprehension processes involved in human information processing, and critically, how information is stored in memory. These findings can be applied to issues inherent in the conceptualization and implementation of digital libraries. This article reviews relevant findings from cognitive research on text comprehension, memory, and spatial cognition with the aim of describing how these concepts apply to the design and functionality of digital libraries. Further, we describe ways in which interdisciplinary collaborations between cognitive psychology and digital library research will be mutually beneficial. Digital libraries can serve as rich test-beds for cognitive theories, while cognitive theories can inform design specifications for digital libraries.

Cultural Heritage Digital Libraries: Needs and Components

This paper describes preliminary conclusions from a long-term study of cultural heritage digital collections. First, those features most important to cultural heritage digital libraries are described. Second, we list those components that have proven most useful in boot-strapping new collections.

Beyond digital incunabula: modeling the next generation of digital libraries

This paper describes several incunabular assumptions that impose upon early digital libraries the limitations drawn from print, and argues for a design strategy aimed at providing customization and personalization services that go beyond the limiting models of print distribution, based on services and experiments developed for the Greco-Roman collections in the Perseus Digital Library. Three features fundamentally characterize a successful digital library design: finer granularity of collection objects, automated processes, and decentralized community contributions.