Research on Implicit Intent Recognition Method Based on Prompt Learning

Abstract As one of the core modules of the dialogue system, intent recognition plays an important role in human-computer interaction. Most of the existing intent recognition research is limited to simple, direct, and explicit intent recognitions. However, the natural human-computer interactions are flexible and diverse, and the expressions are often the euphemistic implicit intentions. Therefore, the implicit intent recognition brings new research challenges in this field. This paper pioneers a Chinese Implicit Intent Dataset CIID, which covers 7 common intents from different fields, and the data is the text containing the user's implicit intent. Based on this corpus, it is the first time prompt learning is employed for implicit intent recognition and by constructing a suitable prompt template, the model can get "relevant hints" to dig out the true intention of the user. Finally, this paper evaluates a range of classification models on CIID dataset. Experimental results show that the recognition rate of the proposed model is 97.6%, and achieves the state-of-the-art recognition accuracy. Furthermore, since it is difficult to collect the user's implicit intention data, this paper also explores the performance of these classification models on the CIID dataset with few-shot settings, and the experimental results show when the training data is reduced to 4.7%, the recognition rate of the proposed model can still keep 92.4%, which is significantly higher than other baseline models, the results further prove this proposed method is advanced and robust.