
Indexado en
Licencia y uso

Citaciones
Análisis de autorías institucional
Ramón-Ferrer V, Badenes-Olmedo C, Corcho OAutor o CoautorRamon Ferrer, VirginiaAutor o CoautorCorcho García, OscarAutor o CoautorAutomatic Topic Label Generation using Conversational Models
Publicado en:K-Cap 2023 - Proceedings Of The 12th Knowledge Capture Conference 2023. 17-24 - 2023-01-01 (), DOI: 10.1145/3587259.3627574
Autores: Ramón-Ferrer V; Badenes-Olmedo C; Corcho O
Afiliaciones
Resumen
In probabilistic topic models, a topic is characterised by a set of words, with a probability associated to each of them. Even though it is not necessary to understand the meaning of topics to perform common downstream tasks where topic models are used, such as topic inference or document similarity, there have been attempts to uncover the semantics of topics by providing labels to them, consisting in a couple of concepts. 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.
Palabras clave
Indicios de calidad
Impacto y visibilidad social
Análisis de liderazgo de los autores institucionales
Existe un liderazgo significativo ya que algunos de los autores pertenecientes a la institución aparecen como primer o último firmante, se puede apreciar en el detalle: Primer Autor (RAMON FERRER, VIRGINIA) y Último Autor (CORCHO GARCIA, OSCAR).