A Text Mining Library for Biodiversity Literature in Spanish JUAN M. BARRIOS ALEJANDRO MOLINA RAUL SIERRA-ALCOCER ENRIQUE-DANIEL ZENTENO-JIMENEZ The National Commission for Knowledge and Use of Biodiversity (CONABIO) ABSTRACT Biodiversity represents a great ecological, economic and aesthetic heritage to the world. Most of the knowledge about this heritage could be found in thousands of documents that describe valuable information obtained over centuries. Projects which try to gather and structure all this information, even for very specific topics, may take years. In addition to this, keeping a project updated is difficult because new knowledge is continuously being published. Therefore, there is a necessity to use automatic methods to extract relevant information efficiently. In this article we describe the first stage of a software project, that aims to build a complete library to apply Natural Language Processing techniques on documents about biodiversity in Spanish. 1. INTRODUCTION This project is part of a large and permanent effort at the National Commission for Knowledge and Understanding of Biodiversity (CONABIO) to gather information about biodiversity in Mexico. The mission of the CONABIO is to promote, coordinate, support and carry out activities aimed at the knowledge of biological diversity in Mexico, and its preservation International Journal of Computational Linguistics and Applications, Vol. 6, No. 2, 2015, pp. 177–192 Received 22/06/2015, Accepted 24/07/2015, Final 23/09/2015. ISSN 0976-0962, http://ijcla.bahripublications.com