Learning from Implicit User Feedback, Emotions and Demographic Information in Task-Oriented and Document-Grounded Dialogues
Dominic Petrak, Thy Thy Tran, Iryna Gurevych
Abstract
Implicit user feedback, user emotions and demographic information have shown to be promising sources for improving the accuracy and user engagement of responses generated by dialogue systems. However, the influence of such information on task completion and factual consistency, which are important criteria for task-oriented and document-grounded dialogues, is not yet known. To address this, we introduce FEDI, the first English task-oriented and document-grounded dialogue dataset annotated with this information. Our experiments with Flan-T5, GPT-2 and Llama 2 show a particularly positive impact on task completion and factual consistency. Participants in our human evaluation reported that the responses generated by the feedback-trained models were more informative (Flan-T5 and GPT-2), relevant and factual consistent (Llama 2).
BibTeX
@inproceedings{petrak-etal-2024-learning,
title = "Learning from Implicit User Feedback, Emotions and Demographic Information in Task-Oriented and Document-Grounded Dialogues",
author = "Petrak, Dominic and
Tran, Thy Thy and
Gurevych, Iryna",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-emnlp.264/",
doi = "10.18653/v1/2024.findings-emnlp.264",
pages = "4573--4603"
}