A Unified Approach to Emotion Detection and Task-Oriented Dialogue Modeling - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2024

A Unified Approach to Emotion Detection and Task-Oriented Dialogue Modeling

Résumé

In current text-based task-oriented dialogue (TOD) systems, user emotion detection (ED) is often overlooked or is typically treated as a separate and independent task, requiring additional training. In contrast, our work demonstrates that seamlessly unifying ED and TOD modeling brings about mutual benefits, and is therefore an alternative to be considered. Our method consists in augmenting SimpleToD, an endto-end TOD system, by extending belief state tracking to include ED, relying on a single language model. We evaluate our approach using GPT-2 and Llama-2 on the EmoWOZ benchmark, a version of MultiWOZ annotated with emotions. Our results reveal a general increase in performance for ED and task results. Our findings also indicate that user emotions provide useful contextual conditioning for system responses, and can be leveraged to further refine responses in terms of empathy.
Fichier principal
Vignette du fichier
IWSDS_Emotion_Aware_TOD_System.pdf (516.8 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04415809 , version 1 (24-01-2024)

Identifiants

  • HAL Id : hal-04415809 , version 1

Citer

Armand Stricker, Patrick Paroubek. A Unified Approach to Emotion Detection and Task-Oriented Dialogue Modeling. IWSDS, Mar 2024, Sapporo (Japon), Japan. ⟨hal-04415809⟩
28 Consultations
22 Téléchargements

Partager

Gmail Facebook X LinkedIn More