The webpage for *Linguistik Indonesia* can be accessed [here][1].
To download the full paper, [click here][2].
To download the Leipzig corpus file used in the paper (i.e. "ind_newscrawl_2012_1M-sentences.txt" [123MB]), [click here][3]. The corpus file has to be put in the same folder with the other data in this project so that it can be accessed when running all codes in the RMarkdown file.
[1]: http://ojs.linguistik-indonesia.org/index.php/linguistik_indonesia
[2]: https://doi.org/10.26499/li.v36i1.71
[3]: https://drive.google.com/file/d/14LddUTSBVZlPLK6U6Gxmkly-om6IL0Z0/view?usp=sharing