Author(s): CONRADO, M. S.; MOURA, M. F.; REZENDE, S. O.

Summary: The notorious advances in textual information storage need fast and effcient tools to organize, retrieve and browse this information and tools for knowledge extraction. A very interesting way to organize specific domain information is the topic taxonomy building. Moreover a great challenge in this research area is the result evaluation and validation. This evaluation can be carried out through objective measures or through a subjective analysis, which is based on the domain specialist judgment. The measures CQM and SQM [1] are used to evaluate a generated taxonomy against a reference taxonomy. A reference taxonomy is constructed by human and consolidated through its community use along the years. The CQM is used to evaluate the generated taxonomy relatively to the selected descriptors for each taxonomy node; on the other hand, the SQM is used to evaluate the taxonomy structure. As these objective measures do not encompass the specialist knowledge, the specialist evaluation is very important. However the human evaluation is expensive, because this task involves readiness, time and dedication from the specialists. In this way, the TaXEm tool claims to reduce the subjective evaluation costs. The TaXEm (Taxonomia em XML da Embrapa) tool offers subsidies for carrying out a taxonomy (semi)automatic evaluation, which allows the user to implement some automatic evaluation before going on a subjective evaluation.

Publication year: 2010

Types of publication: Abstract in annals or event proceedings

Unit: Embrapa Digital Agriculture

Keywords: Information retrieval, Organização da informação, Recuperação da informação, Taxonomia, Taxonomy