ABSTRACT REPRESENTATION FOR MULTI-INTENT SPOKEN LANGUAGE UNDERSTANDING - Archive ouverte HAL
Communication Dans Un Congrès Année : 2023

ABSTRACT REPRESENTATION FOR MULTI-INTENT SPOKEN LANGUAGE UNDERSTANDING

Résumé

Current sequence tagging models based on Deep Neural Network models with pretrained language models achieve almost perfect results on many SLU benchmarks with a flat semantic annotation at the token level such as ATIS or SNIPS. When dealing with more complex human-machine interactions (multi-domain, multi-intent, dialog context), relational semantic structures are needed in order to encode the links between slots and intents within an utterance and through dialog history. We propose in this study a new way to project annotation in an abstract structure with more compositional expressive power and a model to directly generate this abstract structure. We evaluate it on the MultiWoz dataset in a contextual SLU experimental setup. We show that this projection can be used to extend the existing flat annotations towards graph-based structures.
Fichier principal
Vignette du fichier
SLU_on_MW_ICASSP_vf.pdf (212.61 Ko) Télécharger le fichier

Dates et versions

hal-04151466 , version 1 (05-07-2023)

Identifiants

  • HAL Id : hal-04151466 , version 1

Citer

Rim Abrougui, Géraldine Damnati, Johannes Heinecke, Frederic Bechet. ABSTRACT REPRESENTATION FOR MULTI-INTENT SPOKEN LANGUAGE UNDERSTANDING. 2023 IEEE ICASSP - International Conference on Acoustics, Speech, and Signal Processing, IEEE, Jun 2023, Rhodes (Grèce), Greece. ⟨hal-04151466⟩
31 Consultations
77 Téléchargements

Partager

More