A keyword-weighted silhouette-style score evaluates conversational intent clusters without labels, but its formula leaves normalization and zero-overlap cases undefined and validation is anecdotal.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2024 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
KULCQ: An Unsupervised Keyword-based Utterance Level Clustering Quality Metric
A keyword-weighted silhouette-style score evaluates conversational intent clusters without labels, but its formula leaves normalization and zero-overlap cases undefined and validation is anecdotal.