Learning from Implicit User Feedback, Emotions and Demographic Information in Task-Oriented Document-Grounded Dialogues
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 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), more relevant and more factual consistent (Llama 2).
Paper Type: Long
Research Area: Dialogue and Interactive Systems
Research Area Keywords: task-oriented, grounded dialog, knowledge augmented, implicit user feedback, user emotions, demographic information
Contribution Types: NLP engineering experiment, Publicly available software and/or pre-trained models, Data resources
Languages Studied: English
Submission Number: 15
Loading