Fast training of support vector machines using sequential minimal optimization
Advances in kernel methods
ECML '95 Proceedings of the 8th European Conference on Machine Learning
Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data
ICML '01 Proceedings of the Eighteenth International Conference on Machine Learning
QALL-ME needs AIR: a portability study
AdaptLRTtoND '09 Proceedings of the Workshop on Adaptation of Language Resources and Technology to New Domains
Hi-index | 0.00 |
Manual population of institutional repositories with citation data is an extremely time- and resource-consuming process. These costs act as a bottleneck on the fast growth and update of large repositories. This paper aims to describe the AIR system developed at the university of Wolverhampton to address this problem. The system implements a semi-automatic approach for archiving institutional repositories: firstly, it automatically discovers and extracts bibliographical data from the university web site, and, secondly, it interacts with users, authors or librarians, who verify and correct extracted data. The system is integrated with the Wolverhampton Intellectual Repository and E-theses (WIRE), which was designed on the basis of standard software adopted by many UK universities. In this paper we demonstrate that the system can considerably increase the intake of new publication data into an institutional repository without any compromise to its quality.