Need scripts to gather up all unclustered utterances for a given scenario, featurize them, then run them through the cluster classifier to determine the probability that the utterance belongs in each cluster.
We may also include some logic here for prioritizing which utterances are added to the queue first, etc.
Need scripts to gather up all unclustered utterances for a given scenario, featurize them, then run them through the cluster classifier to determine the probability that the utterance belongs in each cluster.
We may also include some logic here for prioritizing which utterances are added to the queue first, etc.