What is it about?
In this paper we propose a methodology, Conversational Probabilistic Topic Labelling (CPTL), to study whether conversational models can be used to generate labels that describe probabilistic topics given their most representative keywords. We evaluate and compare the performance of a selection of conversational models for the topic label generation task with the performance of a task-specific language model trained to generate topic labels.
Featured Image
Photo by Brett Jordan on Unsplash
Read the Original
This page is a summary of: Automatic Topic Label Generation using Conversational Models, December 2023, ACM (Association for Computing Machinery),
DOI: 10.1145/3587259.3627574.
You can read the full text:
Contributors
The following have contributed to this page
