Skip to Main content Skip to Navigation
Conference papers

The importance of fillers for text representations of speech transcripts

Abstract : While being an essential component of spoken language, fillers (e.g. "um" or "uh") often remain overlooked in Spoken Language Understanding (SLU) tasks. We explore the possibility of representing them with deep contextualised embeddings, showing improvements on modelling spoken language and two downstream tasks-predicting a speaker's stance and expressed confidence.
Document type :
Conference papers
Complete list of metadata
Contributor : Pierre Colombo Connect in order to contact the contributor
Submitted on : Friday, February 12, 2021 - 9:49:07 AM
Last modification on : Tuesday, October 19, 2021 - 11:14:15 AM
Long-term archiving on: : Thursday, May 13, 2021 - 6:28:51 PM


Files produced by the author(s)



Tanvi Dinkar, Pierre Colombo, Matthieu Labeau, Chloé Clavel. The importance of fillers for text representations of speech transcripts. Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), Association for Computational Linguistics, Nov 2020, Online, Dominican Republic. pp.7985-7993, ⟨10.18653/v1/2020.emnlp-main.641⟩. ⟨hal-03134854⟩



Record views


Files downloads