Skip to Main content Skip to Navigation
Conference papers

The importance of fillers for text representations of speech transcripts

Tanvi Dinkar 1 Pierre Colombo 1 Matthieu Labeau 1 Chloé Clavel 1, 2
1 LTCI - Laboratoire Traitement et Communication de l'Information
2 Télécom ParisTech
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.
Keywords : Fillers Text representations Spoken Language Understanding
Document type :
Conference papers
Complete list of metadata
https://hal.archives-ouvertes.fr/hal-03134854
Contributor : Pierre Colombo <>
Submitted on : Friday, February 12, 2021 - 9:49:07 AM
Last modification on : Wednesday, February 24, 2021 - 3:28:26 PM

File

Vignette du document
Final_EMNLP_2020.pdf
Files produced by the author(s)

Identifiers

Collections

INSTITUT-TELECOM | PARISTECH | LTCI | IP_PARIS

Citation

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⟩

Export

BibTeX TEI DC DCterms EndNote

Share

Metrics

Record views

65

Files downloads

23