id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
work_6g5fvv6mtnfuvogiz3otmgdzum	Jelena Prokić	Recognising Groups among Dialects	2008	24	.pdf	application/pdf	6532	514	67	such as hierarchical clustering algorithms used to detect groups within certain dialect Without proper evaluation, it is very hard to determine if the results of the applied clustering technique are an artifact of the algorithm or the detection of real groups The aim of this paper is to evaluate algorithms used to detect groups among language dialect varieties measured at the aggregate level. In order to evaluate the performance of different clustering algorithms, all sites present in our data set were manually put by an expert in one of the two, Noisy clustering, that was applied with the seven hierarchical algorithms, has confirmed that there are two relatively stable groups in the data: Eastern and Western. Different clustering validation methods have shown that three algorithms are not suitable at all for the data we are working with, namely single link, UPGMC and WPGMC.	./cache/work_6g5fvv6mtnfuvogiz3otmgdzum.pdf	./txt/work_6g5fvv6mtnfuvogiz3otmgdzum.txt