Abstract: In this paper, we propose two frameworks to support automatic medical consultation, namely doctor-patient dialogue understanding and diagnosis-oriented interaction. A new medical dialogue dataset with multi-level fine-grained annotations is introduced and five evaluation tasks are established, including medical named entity recognition, dialogue act classification, symptom recognition, medical report generation and diagnosis-oriented dialogue system. We report a set of benchmark results for each track, which shows the usability of the dataset and sets a baseline for future studies.
0 Replies
Loading