K-ESConv: Knowledge Injection for Emotional Support Dialogue Systems via Prompt Learning
This work addresses the need for more effective emotional support dialogue systems, though it appears incremental as it builds on existing prompt learning and retrieval methods.
The paper tackles the problem of generating emotionally supportive dialogue responses by injecting professional knowledge from online counseling forums, achieving superior performance over existing baselines on both automatic and human evaluations.
Automatic psychological counseling requires mass of professional knowledge that can be found in online counseling forums. Motivated by this, we propose K-ESConv, a novel prompt learning based knowledge injection method for emotional support dialogue system, transferring forum knowledge to response generation. We evaluate our model on an emotional support dataset ESConv, where the model retrieves and incorporates knowledge from external professional emotional Q\&A forum. Experiment results show that the proposed method outperforms existing baselines on both automatic evaluation and human evaluation, which shows that our approach significantly improves the correlation and diversity of responses and provides more comfort and better suggestion for the seeker.