Leveraging Medical Discourse to Answer Complex Questions

We review the literature on medical discourse and attempt to build a computational model of it. Medical discourse sheds a light on communication structure of patient-doctor and other communication scenarios in healthcare and should be leveraged to facilitate and automate this communication when it is possible and practical. We propose a unified framework to represent communication discourse at the meta-level, where the subject of the communication is expressed in a language object.

So far, the broad range of work on medical discourse is detached from computational discourse analysis, and we explore the possibilities of filling this gap and computationally treat the peculiarities of how information is passed between the agents in a hospital setting. We encode such discourse-level features as social interaction, critical discourse, metaphoric language, and representation of pain.

We select the domain of question answering (QA) against a corpus of medical documents of diverse nature to evaluate our computational model of medical discourse. We compare the performance of our discourse-enriched prompt-base models with the ones without manual discourse feature engineering. It turns out that applying specific structures obtained in medical discourse studies improves the relevance and efficiency of question answering. We pro also propose a RAG architecture leveraging discourse analysis.

https://github.com/bgalitsky/medical_discourse

Speaker: Boris Galitsky