kth.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Classification of Feedback Functions in Spoken Dialog Using Large Language Models and Prosodic Features
Furhat Robotics.
Aix-Marseille Université.ORCID iD: 0000-0001-7919-5688
KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Speech, Music and Hearing, TMH.ORCID iD: 0000-0002-8579-1790
2023 (English)In: 27th Workshop on the Semantics and Pragmatics of Dialogue, Maribor: University of Maribor , 2023, p. 15-24Conference paper, Published paper (Refereed)
Abstract [en]

Feedback utterances such as ‘yeah’, ‘mhm’,and ‘okay’, convey different communicative functions depending on their prosodic realizations, as well as the conversational context in which they are produced. In this paper, we investigate the performance of different models and features for classifying the communicative function of short feedback tokens in American English dialog. We experiment with a combination of lexical and prosodic features extracted from the feedback utterance, as well as context features from the preceding utterance of the interlocutor. Given the limited amount of training data, we explore the use of a pre-trained large language model (GPT-3) to encode contextual information, as well as SimCSE sentence embeddings. The results show that good performance can be achieved with only SimCSE and lexical features, while the best performance is achieved by solely fine-tuning GPT-3, even if it does not have access to any prosodic features.

Place, publisher, year, edition, pages
Maribor: University of Maribor , 2023. p. 15-24
National Category
Language Technology (Computational Linguistics)
Identifiers
URN: urn:nbn:se:kth:diva-341388OAI: oai:DiVA.org:kth-341388DiVA, id: diva2:1821225
Conference
27th Workshop on the Semantics and Pragmatics of Dialogue, 16th and 17th August 2023, University of Maribor, Faculty of Electrical Engineering and Computer Science, Maribor, Slovenia
Note

QC 20231220

Available from: 2023-12-19 Created: 2023-12-19 Last updated: 2023-12-20Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Conference websiteProceedings

Authority records

Skantze, Gabriel

Search in DiVA

By author/editor
Ochs, MagalieSkantze, Gabriel
By organisation
Speech, Music and Hearing, TMH
Language Technology (Computational Linguistics)

Search outside of DiVA

GoogleGoogle Scholar

urn-nbn

Altmetric score

urn-nbn
Total: 55 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf