Enhancing Relational Topic Models with Named Entity Induced Links.

Felix Kuhr, Mathis Lichtenberger, Tanya Braun, Ralf Möller


Relational topic modeling as an extension to classical topic modeling assumes that documents with some form of link between the documents share topics. The links between documents are given from hyperlinks in web documents, citations in articles, or friendships in social networks. In this work, we consider links between documents induced from named entities: Two documents are linked to each other if both documents have a named entity in common. We present a case study on the performance of relational topic modeling using named-entity induced links between documents. Comparing the prediction accuracy with different sets of named-entity induced links, the results show that additional links between documents can increase the performance of topic models.
Original languageEnglish
Title of host publicationICSC
Number of pages4
Publication date2021
Publication statusPublished - 2021

Research Areas and Centers

  • Centers: Center for Artificial Intelligence Luebeck (ZKIL)
  • Research Area: Intelligent Systems


Dive into the research topics of 'Enhancing Relational Topic Models with Named Entity Induced Links.'. Together they form a unique fingerprint.

Cite this