Summarize Medical Conversations
Posted on 0 Comments
This note is for Song, Y., Tian, Y., Wang, N., & Xia, F. (2020). Summarizing Medical Conversations via Identifying Important Utterances. Proceedings of the 28th International Conference on Computational Linguistics, 717–729.
The summarization systems for conversations need to extract salient contents from spontaneous utterances by multiple speakers.
- focus on medical conversation summarization, using a dataset of medical conversations and corresponding summaries which were crawled from a well-known online healthcare service provider in China.
- propose a hierarchical encoder-tagger model (HET) to generate summaries by identifying important utterances (with respect to problem proposing and solving) in the conversations.
- high-quality summaries can be generated by extracting two types of utterances, problem statements and treatment recommendations.
- experimental results demonstrate that HET outperforms strong baselines and models from previous studies, and adding conversation-related features can further improve system performance.