Chinese Medical Intent Recognition Based on Multi-feature Fusion

The increasing popularity of online query services has heightened the need for suitable methods to accurately understand the truth of query intention. Currently, most of the medical query intention recognition methods are deep learning-based. Because of the inadequate of corpus of the medical field in the pre-trained phase, these methods may fail to accurately extract the text feature constructed by medical domain knowledge. What’s more, they rely on a single technology to extract the text information, and can’t fully capture the query intention. To mitigate these issues, in this paper, we propose a novel intent recognition model called EDCGA (ERNIE-Health+D-CNN+Bi-GRU+Attention). EDCGA achieves text representation using the word vectors of the pre-trained ERNIE-Health model and employs D-CNN to expand the receptive field for extracting local information features. Meanwhile, it combines Bi-GRU and attention mechanism to extract global information to enhance the understanding of the intent. Extensive experimental results on multiple datasets demonstrate that our proposed model exhibits superior recognition performance compared to the baselines.