@article{2008-SoftSpectralClustering-0810.1261
, author={Richard Nock and Pascal Vaillant and Frank Nielsen and Claudia Henry}
, title={Soft Uncoupling of Markov Chains for Permeable Language Distinction: A New Algorithm}
, journal={Computing Research Repository (CoRR)}
, month={October}
, year={2008}
, volume={abs/0810.1261}
, abstract={
Without prior knowledge, distinguishing different languages may be a hard task,
 especially when their borders are permeable. We develop an extension of spectral
 clustering -- a powerful unsupervised classification toolbox -- that is shown to
 resolve accurately the task of soft language distinction. At the heart of our approach,
 we replace the usual hard membership assignment of spectral clustering by a soft,
 probabilistic assignment, which also presents the advantage to bypass a well-known
 complexity bottleneck of the method. Furthermore, our approach relies on a novel,
 convenient construction of a Markov chain out of a corpus. Extensive experiments
 with a readily available system clearly display the potential of the method, which
 brings a visually appealing soft distinction of languages that may define altogether
 a whole corpus. 
}
}