G2T: A Simple but Effective Framework for Topic Modeling based on Pretrained Language Model and Community Detection. (arXiv:2304.06653v2 [cs.CL] UPDATED)

It has been reported that clustering-based topic models, which cluster
high-quality sentence embeddings with an appropriate word selection method, can
generate better topics than generative probabilistic topic models. However,
these approaches suffer from the inability to select appropriate parameters and
incomplete models that overlook the quantitative relation between words with
topics and topics with text. To solve these issues, we propose graph to topic
(G2T), a simple but effective framework for topic modelling. The framework is
composed of four modules. …

arxiv cluster clustering community detection embeddings framework generative graph language language model modeling modelling modules pretrained language model quality quantitative text topic modeling topics word words