The specification of the language of the field and interoperability: cross-language access to catalogues and online libraries (CACAO)

Authors:
Barbara Levergood;Stefan Farrenkopf;Elisabeth Frasnelli
Affiliations:
Goettingen State and University Library, Germany;Goettingen State and University Library, Germany;Library of the Free University of Bozen-Bolzano, Italy
Venue:
DCMI '08 Proceedings of the 2008 International Conference on Dublin Core and Metadata Applications
Year:
2008

Citing 1
Cited 0

Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition

Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

The CACAO Project (Cross-language Access to Catalogues and Online Libraries) has been designed to implement natural language processing and cross-language information retrieval techniques to provide cross-language access to information in libraries, a critical issue in the linguistically diverse European Union. This project report addresses two metadata-related challenges for the library community in this context: "false friends" (identical words having different meanings in different languages) and term ambiguity. The possible solutions involve enriching the metadata with attributes specifying language or the source authority file, or associating potential search terms to classes in a classification system. The European Library will evaluate an early implementation of this work in late 2008.