GINopic: Topic Modeling with Graph Isomorphism Network
This work addresses the need for better topic modeling in natural language processing by incorporating word dependencies, though it appears incremental as it builds on existing graph-based and embedding methods.
The authors tackled the problem of topic modeling by proposing GINopic, a framework that uses graph isomorphism networks to capture word correlations, and demonstrated its effectiveness through evaluations on benchmark datasets.
Topic modeling is a widely used approach for analyzing and exploring large document collections. Recent research efforts have incorporated pre-trained contextualized language models, such as BERT embeddings, into topic modeling. However, they often neglect the intrinsic informational value conveyed by mutual dependencies between words. In this study, we introduce GINopic, a topic modeling framework based on graph isomorphism networks to capture the correlation between words. By conducting intrinsic (quantitative as well as qualitative) and extrinsic evaluations on diverse benchmark datasets, we demonstrate the effectiveness of GINopic compared to existing topic models and highlight its potential for advancing topic modeling.