This is the repository for the dataset created for the paper **Infusing Emotions into Task-oriented Dialogue Systems: Understanding, Management, and Generation**, which will be presented at SIGDIAL 2024.
This is the repository for the dataset created for the paper **Infusing Emotions into Task-oriented Dialogue Systems: Understanding, Management, and Generation** presented at SIGDIAL 2024.
This dataset contains additional manually labelled **system emotional conduct** annotations for the original [EmoWOZ dataset](https://zenodo.org/records/6506504).
This dataset contains additional manually labelled **system emotional conduct** annotations for the original [EmoWOZ dataset](https://zenodo.org/records/6506504).
The dataset will be uploaded to Zenodo.org and the link will also be updated here when the paper becomes publicly available.
The dataset can be found at Zenodo.org: https://zenodo.org/records/14810836. The dataset itself is a JSON file containing a dictionary where the key is `{multiwoz_dialogue_id}-{turn_index}` and the value is the numerical label. The meaning of the label is as following:
\ No newline at end of file
- 0: neutral
- 1: compassionate
- 2: apologetic
- 3: enthusiastic
- 4: appreciative
In the same Zenodo page, you will also find checkpoints for all pipeline modules of the emotional system proposed in the paper.
** Citation
@inproceedings{feng-etal-2024-infusing,
title = "Infusing Emotions into Task-oriented Dialogue Systems: Understanding, Management, and Generation",
author = "Feng, Shutong and
Lin, Hsien-chin and
Geishauser, Christian and
Lubis, Nurul and
van Niekerk, Carel and
Heck, Michael and
Ruppik, Benjamin Matthias and
Vukovic, Renato and
Gasic, Milica",
editor = "Kawahara, Tatsuya and
Demberg, Vera and
Ultes, Stefan and
Inoue, Koji and
Mehri, Shikib and
Howcroft, David and
Komatani, Kazunori",
booktitle = "Proceedings of the 25th Annual Meeting of the Special Interest Group on Discourse and Dialogue",
month = sep,
year = "2024",
address = "Kyoto, Japan",
publisher = "Association for Computational Linguistics",
abstract = "Emotions are indispensable in human communication, but are often overlooked in task-oriented dialogue (ToD) modelling, where the task success is the primary focus. While existing works have explored user emotions or similar concepts in some ToD tasks, none has so far included emotion modelling into a fully-fledged ToD system nor conducted interaction with human or simulated users. In this work, we incorporate emotion into the complete ToD processing loop, involving understanding, management, and generation. To this end, we extend the EmoWOZ dataset (Feng et al., 2022) with system affective behaviour labels. Through interactive experimentation involving both simulated and human users, we demonstrate that our proposed framework significantly enhances the user`s emotional experience as well as the task success."
