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

Abstract

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.

Accepted @ IWSDS 2024

References in corpus (6)

• Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
• Llama 2: Open Foundation and Fine-Tuned Chat Models
• LoRA: Low-Rank Adaptation of Large Language Models
• DailyDialog: A Manually Labelled Multi-turn Dialogue Dataset
• EmoUS: Simulating User Emotions in Task-Oriented Dialogues
• EmoWOZ: A Large-Scale Corpus and Labelling Scheme for Emotion Recognition in Task-Oriented Dialogue Systems