UPDF AI

Topic Modeling Using Collapsed Typed Dependency Relations

Elnaz Delpisheh,Aijun An

2014 · DOI: 10.1007/978-3-319-06605-9_13
Pacific-Asia Conference on Knowledge Discovery and Data Mining · 2 Citations

TLDR

A novel topic model is proposed that enriches text documents with collapsed typed dependency relations to effectively acquire syntactic and semantic dependencies between consecutive and nonconsecutive words of text documents and to enforce coherent topic assignments for conceptually similar words by generalizing words with their synonyms.