Meetings are increasingly important for collaborations. Action items in meeting transcripts are crucial for managing post-meeting to-do tasks, which usually are summarized laboriously.
The Action Item Detection task aims to automatically detect meeting content associated with action items. However, datasets manually annotated with action item detection labels are scarce and in small scale. We construct and release the first Chinese meeting corpus with manual action item annotations (Our data: https://www.modelscope.cn/datasets/modelscope/Alimeeting4MUG/summary). In addition, we propose a Context-Drop approach to utilize both local and global contexts by contrastive learning, and achieve better accuracy and robustness for action item detection. We also propose a Lightweight Model Ensemble method to exploit different pre-trained models (Our codebase: https://github.com/alibaba-damo-academy/SpokenNLP/tree/main/action-item-...). Experimental results on our Chinese meeting corpus and the English AMI corpus demonstrate the effectiveness of the proposed approaches.