A Unified Approach to Emotion Detection and Task-Oriented Dialogue Modeling
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909232680402944 |
|---|---|
| author | Stricker, Armand Paroubek, Patrick |
| author_facet | Stricker, Armand Paroubek, Patrick |
| contents | 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 end-to-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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_13789 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | A Unified Approach to Emotion Detection and Task-Oriented Dialogue Modeling Stricker, Armand Paroubek, Patrick Computation and Language 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 end-to-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. |
| title | A Unified Approach to Emotion Detection and Task-Oriented Dialogue Modeling |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2401.13789 |