How to rank terminology extracted by Exterlog

Abstract

In many application areas, systems reports occurring events in a kind of textual data called usually log files. Log files report the status of systems, products, or even causes of problems that can occur. The Information extracted from log files of computing systems can be considered one of the important resources of information systems. Log files are considered as a kind of "complex textual data", i.e. the multi-source, heterogeneous, and multi-format data. In this paper, we aim particularly at exploring the lexical structure of these log files in order to extract the terms used in log files. These terms will be used in the building of domain ontology and also in enrichment of features of log files corpus. According to features of such textual data, applying the classical methods of information extraction is not an easy task, more particularly for terminology extraction. Here, we introduce a new developed version of Exterlog, our approach to extract the terminology from log files, which is guided by Web to evaluate the extracted terms. We score the extracted terms by a Web and context based measure. We favor the more relevant terms of domain and emphasize the precision by filtering terms based on their scores. The experiments show that Exterlog is well-adapted terminology extraction approach from log files. © 2011 Springer-Verlag.