Dialogue Term Extraction using Transfer Learning and Topological Data Analysis
[Renato Vukovic,
Michael Heck,
Benjamin Matthias Ruppik,
Carel van Niekerk,
Marcus Zibrowius,
Milica Gasic]
We demonstrate that topological features derived from neighborhoods
in a word embedding can be used to extract dialogue terms.
In particular, the Wasserstein norm and Persistence Image Vectorization
of the persistent homology of the neighborhood appear to be generalizable
features which are effective in a transfer learning approach.
Proceedings of the 23rd Annual Meeting of the Special Interest Group on
Discourse and Dialogue (SIGDIAL 2022), pages 564-581, Edinburgh, UK
doi:10.18653/v1/2022.sigdial-1.53
arXiv:2208.10448