[The] academic chairman noted [the] secretary['s] considerable measurements. /
University employee[']s attorney indicated [the] administrative committee. /
Literary agencies particularly fiscal. /
drums come in
rhythm guitar and bass come in
main riff begins
Carnivore (Pete Steele's band before Type O Negative) also did it in 1987 (although it's probably not going to be classified as a metal song unless your name is Marcel Duchamp or Tracy Enim): https://www.youtube.com/watch?v=eGDTrWw_APM
(which may not be particularly metal, but they have an interesting contrast between their sound and their lyrics)
The lyrics are a german recipe on how to make cookies without eggs....
I have the feeling it is not just an unsolved problem, but also an undefined problem.
This was interesting to read in general though, especially as someone who listens to metal quite frequently (mostly of the power metal variety).
I don't think it's a problem with the song data. When the algorithm picks a song it considers most lyrically representative of a band, it chooses from all the songs in the dataset, and it doesn't always pick a song by that band.
LSTMetallica: Generation drum tracks by learning the drum tracks of 60 Metallica songs
Keunwoo is also the translator of Deeplearning4j's Korean site:
Given a text it will split each word, add up the metalness score and divide it by the number of words.
I found it amusing that Venom and Running Wild are grouped together in the first step. But well, by the lyrics it fits. The rest matches my expectations surprisingly well.
I wonder if the clustering method can be used/is used by apps like Spotify to create a list of "related bands", as the graph at the end was fairly accurate.