The-Ineffable-Alias
The-Ineffable-Alias
i've used BERTopic to cluster occupations (the results are awesome taking into account the poor context and the messiness of the dataset) and now i want to classify them by...
what metrics are probably a good idea for high-dimensional topic modeling? (i know cosine is one of them for other use cases at least)
i've used bertopic to group occupations (of a dataframe column) by type (health, finance, etc). it worked pretty well. (thanks!) particularly taking into account it's a hard use case (nlp...
is optuna and the like a good fit for bertopic?
i've been dealing with bertopic bugs all day (this, pyaml related, etc) :|. still, amazing tool. 