You're currently viewing an old version of this dataset. To see the current version, click here.

StreamHover: Livestream Transcript Summarization and Annotation

StreamHover is a framework for annotating and summarizing livestream transcripts. It uses a neural extractive summarization model that leverages vector-quantized variational autoencoder to learn latent vector representations of spoken utterances and identify salient utterances from the transcripts to form summaries.

Data and Resources

Cite this as

Sangwoo Cho, Franck Dernoncourt, Tim Ganter, Trung Bui, Nedim Lipka, Hassan Foroosh, Fei Liu (2024). Dataset: StreamHover: Livestream Transcript Summarization and Annotation. https://doi.org/10.57702/xxvjs6q4

DOI retrieved: December 2, 2024

Additional Info

Field Value
Created December 2, 2024
Last update December 2, 2024
Defined In https://doi.org/10.48550/arXiv.2109.05160
Author Sangwoo Cho
More Authors
Franck Dernoncourt
Tim Ganter
Trung Bui
Nedim Lipka
Hassan Foroosh
Fei Liu
Homepage https://github.com/ucfnlp/streamhover