Towards Semantic Modeling of Contradictions and Disagreements: A Case Study of Medical Guidelines
This work addresses the need for formal reasoning about contradictory medical guidelines, which is a domain-specific problem for healthcare and NLP practitioners.
The paper tackles the problem of distinguishing contradictions from disagreements in natural language texts, specifically in medical guidelines, and reports positive evaluation results on a small corpus of contradictory medical recommendations.
We introduce a formal distinction between contradictions and disagreements in natural language texts, motivated by the need to formally reason about contradictory medical guidelines. This is a novel and potentially very useful distinction, and has not been discussed so far in NLP and logic. We also describe a NLP system capable of automated finding contradictory medical guidelines; the system uses a combination of text analysis and information retrieval modules. We also report positive evaluation results on a small corpus of contradictory medical recommendations.