@proceedings {384, title = {Building a nasa yuwe language test collection}, journal = {16th International Conference on Intelligent Text Processing and Computational Linguistics, CICLing 2015}, volume = {9041}, year = {2015}, month = {Abril 2015}, publisher = {Springer}, edition = {2015}, address = {El Cairo, Egipto}, abstract = {

The nasa yuwe is the language of the Paez people in Colombia is currently an endangered language[1]. The nasa community has therefore been reviewing different strategies with the purpose of encouraging 1) the visualization process of the language and 2) the sensibilization of the use of the language, by means of computational tools. With the intention of making a contribution to both of these areas, the building of an information retrieval system (IRS) for texts written in Nasa Yuwe is proposed. This would be expected to encourage writing in Nasa Yuwe and the retrieval of documents written in the language. To implement the system, it is necessary to have a test collection with which to assess the IRS, so that the first step, prior to IRS development, is to build that test collection specifically for Nasa Yuwe texts, something which is not currently available. This paper thus presents the first test collection in Nasa Yuwe, as well as showing its construction process and results. The results allow appreciation of:1) the process of building the Nasa Yuwe test collection, 2) the queries, expert opinions and documents; and 3) a statistical analysis of the data, including an analysis of Zipf\’s Law[2].

}, issn = {978-3-319-18110-3 }, url = {http://link.springer.com/chapter/10.1007/978-3-319-18111-0_9}, author = {Luz Marina Sierra Mart{\'\i}nez and Juan Carlos Corrales and Carlos Alberto Cobos Lozada and Tulio Rojas Curieux} }