@@ -11,7 +11,7 @@ This repository contains my exercise sheets and final project for <a href="https
This project takes as input a text in a particular Slavic language and returns which language it is, including information about the linguistic classification of that language.
## Motivation
Although many language detectors already exist, there are, as far as I can tell, none which focus specifically on the Slavic language family and are thus able to detect less widely-spoken Slavic languages such as Lower Sorbian or Rusyn. However, using the fact that Wikipedia is available in many of this smaller languages, a classifier can be trained, as is explained below, to detect these minority languages. Such a classifier can help towards preservation of these languages, and can contribute to their digital presence, thus encouraging speakers to use them.
Although many language detectors already exist, there are, as far as I can tell, none which focus specifically on the Slavic language family and are thus able to detect less widely-spoken Slavic languages such as Lower Sorbian or Rusyn. However, using the fact that Wikipedia is available in many of these smaller languages, a classifier can be trained, as is explained below, to detect these minority languages. Such a classifier can help towards preservation of these languages, and can contribute to their digital presence, thus encouraging speakers to use them.
More information about the Slavic language classifier can be found <ahref="https://gitlab.cl.uni-heidelberg.de/innes/exp-ml-1/-/tree/master/project">here</a>.
