Multi-Granularity Prompts for Topic Shift Detection in Dialogue
This work addresses topic shift detection in dialogues, which is important for improving conversational AI systems, but it appears incremental as it builds on existing prompt-based methods.
The paper tackled dialogue topic shift detection by using a prompt-based approach to extract multi-granularity topic information, resulting in a model that outperformed baselines on Chinese CNTD and English TIAGE datasets.
The goal of dialogue topic shift detection is to identify whether the current topic in a conversation has changed or needs to change. Previous work focused on detecting topic shifts using pre-trained models to encode the utterance, failing to delve into the various levels of topic granularity in the dialogue and understand dialogue contents. To address the above issues, we take a prompt-based approach to fully extract topic information from dialogues at multiple-granularity, i.e., label, turn, and topic. Experimental results on our annotated Chinese Natural Topic Dialogue dataset CNTD and the publicly available English TIAGE dataset show that the proposed model outperforms the baselines. Further experiments show that the information extracted at different levels of granularity effectively helps the model comprehend the conversation topics.