Download Pdf The PPT/PDF document "ccobos jcorral" is the property of its rightful owner. Permission is granted to download and print the materials on this web site for personal, non-commercial use only, and to display it on your personal computer provided you do not modify the materials and that you retain all copyright notices contained in the materials. By downloading content from our website, you accept the terms of this agreement.
1 Popayán, Colombia { lsierra , ccob
Popayán, Colombia { lsierra , ccobos, jcorral } @ unicauca.edu.co Abstract . In Colombia, ethnic and cultural diversity is conceived by the government to be a social right. S
2 uch diversity find s expression, am
uch diversity find s expression, among other ways, in a large number of indigenous languages , which have been kept alive for cen turies. However, efforts toward conservat
3 ion means of IR activities. Th ese enco
ion means of IR activities. Th ese encourage different, new possibilities for the Nasa people to be able to interact in Nasa Yuwe. It has therefore become necessary to adapt the st
4 ages of the IR process to this languag
ages of the IR process to this language. The current paper specifically presents a process for adapting a t okenizer to texts written in Nasa Yuwe. This involves making use of the
5 precision - recall curve as an evaluat
precision - recall curve as an evaluation and comparison measure. The results presented allow appreciation of all stages in the process of adapting the standard tokenizer to produce t
6 he Nasa has recently been classified
he Nasa has recently been classified as independent and currently in the process of description. It is still not entirely clear in what way many aspects of its grammar, syntax, m
7 orphology, semantics, and of other lin
orphology, semantics, and of other linguistic layers are to be seen in order to analyze this language in its writte n variant [4]. This is due to the fact that Nasa Yuwe has alw
8 ays been a language of oral tradition.
ays been a language of oral tradition. Only in 1964 an alphabet was first proposed for writing purposes . But only in year 2000 a unified alphabet became available. However, st
9 ill t here , and the results obtaine
ill t here , and the results obtained , using the tokenizer adapted for Nasa Yuwe, thus representing a major advance in the process of building an Information Retrieval (IR) syst
10 em for texts written in Nasa Yuwe. It is
em for texts written in Nasa Yuwe. It is expected to offer a tool that allows Nasa people to interact in a computational environment in their own language, encouraging writing and
11 thereby contributing to the visibility
thereby contributing to the visibility of the language by means of computational tools. The rest of th e paper is organized as fol lows. Section 2 presents a background on IR for t