Overview of the NLPCC 2023 Shared Task: Chinese Medical Instructional Video Question Answering.

In this paper, we present an overview of the NLPCC 2023 shared task, named Chinese Medical Instructional Video (CMIVQA), which includes three sub-tracks: temporal answer grounding in a single video, video corpus retrieval, and temporal answer grounding in video corpus. The CMIVQA datasets containing the videos, audios, and corresponding subtitles are made public, and the corresponding labels are manually annotated by medical experts. Details of the shared task, datasets, evaluation metrics, and final results will be provided in order. We hope this shared task can provide more insights into the first-aid, medical emergency, or medical education.